# What's the difference between the grid and the chat?
Source: https://docs.coloop.ai/ai-skills-hub/advanced-analysis/ai-chat-vs-ai-grids
## The Analysis Grid
* The analysis grid and the chat use a similar underlying approach
* The analysis grid contains a 'baked in' prompt
* It is less flexible and will focus on giving thematic summaries
* Providing a discussion guide will also cause it to provide suggested questions
* We recommend starting with the Analysis Grid if you haven't used many AI tools before
## The Chat
* The chat is much less constrained than the Analysis Grid
* It is much more flexible but requires some experimentation to get the prompts right
* We recommend reading [this guide](./writing-good-prompts/basics) to understand more
# Comparison with ChatGPT
Source: https://docs.coloop.ai/ai-skills-hub/advanced-analysis/comparison-with-chatgpt
| Feature | CoLoop | ChatGPT |
| ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Integrations** | Recollective; Incling; Excel Formats; Transcript Formats; Audio and Video; Zoom\*; MS Teams\*; G Meet\*; Translation built in Even more coming soon... | Some capabilities here inherently and via plugins with 3rd parties; no file management capabilities; all files are treated as binaries or text so has no notion of: speakers; tasks; activities; questions; segments or filters. |
| **Transcription accuracy** | 43% fewer WER than Whisper on real world data | Lower accuracy; uses Whisper; also can’t handle speaker labelling |
| **Analysis grids** | Filter; compare; contrast and analyse across documents. View everything in a familiar UI; Suggested questions and minimal learning curve. Optimised to extract themes; also provides theme counts | Limited to chat UI; Doesn’t reliably cite sources |
| **Research Specialisation** | Uses discussion guides; background information and speaker roles to 10x performance on qual analysis task | Generalised tool |
| **Clip Reels** | Can easily select and generate clips in 1 click (up to 6Gb per file) | Can be done via code interpreter for small video files (less than 512MB per file) |
| **Segmentation** | Can handle participant segments and answer questions about them | Has no notion of speaker roles or segments; highly unreliable at distinguishing between them |
| **Support** | Highly available support team | No support |
| **Context limits / accuracy** | Backed by a qual specific data model and search engine; reduces, enriches and constructs evidence before responding Proven accuracy up to 100 hours worth of interviews. | Fills entire context with as much info as possible regardless of its relevance (max 100,000 words \~ 10 hours audio). Good at answering questions about single documents but prone to hallucinate when working across many. |
| **Vendor lock in** | Will always use best available models whoever they are from: Gemini / Claude / Mistral etc. Also includes hybrid / agentic approaches e.g. Gemini + GPT4 or Mistral + Claude. | Will only ever use OpenAI models |
| **Data privacy** | Will always guarantee this; Key to our operating model; fully insured | Frequently change their terms and are subject to competing interest for their customer facing products |
| **Access Management & Collaboration** | Can access manage projects and share resources; files and more across teams selectively; will continue to develop specifically for agency work. | Limited collaboration capabilities |
# Open Ended Data
Source: https://docs.coloop.ai/ai-skills-hub/advanced-analysis/open-ended-data
CoLoop can be used to analyse small amounts of open ended data qualitatively. The video below explains how custom analysis grids and AI chats can be used to explore some of the qualitative themes within your open ended data.
## Preparing your data
When using CoLoop to analyse open ended be sure to:
* **Unique Names**: Make sure each of your participants has a unique name. If names weren't collected you can apply a pseudonymous name e.g. "Participant 1"; "Participant 2" etc.
* **Segmentation Information**: Include segmentation information with your open ends e.g. divide up responses by demographic.
* **Descriptive Titles**: Give your columns descriptive titles so the AI actually 'understands' what participants are responding to.
## Using Custom Analysis Grids
* Create a new custom analysis grid after importing your data.
* Add rows corresponding to segments you wish to analyze (e.g., number of stars given in reviews).
* Pose questions within the grid to generate thematic overviews based on segment responses.
## Using the AI Chat
* Create a new AI chat and scope it to the excel files, sheets or even individual columns you want to analyse
* Ask specific questions or request examples and quotes related to identified themes.
* Click through on any outputs to see direct evidence and context verification.
## Limitations
* CoLoop does not support coding functionality, making it less suitable for quantitative analyses of large datasets.
* Basic analysis grids are limited to handling up to 150 participants. Larger datasets require alternative methods like custom grids or AI chat that use sampling strategies.
* Excel file uploads are capped at files with up to 500 rows. Larger datasets need segmentation into smaller files.
# Writing a Good Project Description
Source: https://docs.coloop.ai/ai-skills-hub/advanced-analysis/writing-good-proj-desc
* CoLoop's performance can be **massively** improved by providing it with a good project description.
* This description will be used fed into the AI model at inference and used to guide its output.
* You can update this description at any point by clicking on the project settings in the top menu.
* This article outlines some recommendations and best practices when using the project description.
## How does CoLoop actually use this information?
* The description provided is considered used by CoLoop in:
1. AI Chats
2. Analysis Grids
3. Summaries.
4. Processing of documents
5. Evidence Panels
6. Suggested Questions
* It also helps to resolve reference to concepts or products in a discussion
### For example a query such as...
> Summarise what the customers thought?
With a project description like...
> This project contains feedback interviews with users of a new product for qualitative research called CoLoop. Participants are talking about their experiences with the tool. I am interesting in summarising the main gain points, pain points and areas for further improvement. I am also interested in keeping track of any follow up items they are expecting me to send to them after the call.
For CoLoop can then effectively be read as...
> Summarise **\[into gain points, pain points and areas for improvement]** what the customers **\[of a new tool CoLoop]** thought **\[of that tool]**
## So how do I set the project description?
### Set the description when creating a project
You will be prompted to set the project description when you create the project at the beginning:
### Set the description after you've created a project
You can also go back at any point and set / update the project description by clicking on the button next to the project name in the menu on the lHS:
### Automatically generate a description
If you've uploaded a discussion guide you can get CoLoop to generate a description for you automatically by clicking the generate button.
## What kind of things can I put in the description?
The project description is a great place to put information that you don't want to have to keep repeating in every single message e.g.
* Background context about the study
* Details of the different concepts being referred to
* Objectives or questions your trying to answer
* Industry specific details or acronyms
* Guidance for how you want the chat to layout answers to your questions
## What if my project has multiple discussion guides?
* If you have multiple discussion guides most of the time we recommend copy and pasting them into one document.
* CoLoop uses the uploaded guide to create a description of the project, see examples of questions asked and derive a set of objectives.
* These can always be edited afterwards so you can ensure the AI has a good understanding of what question you're trying to answer.
# How do I write good prompts?
Source: https://docs.coloop.ai/ai-skills-hub/advanced-analysis/writing-good-prompts/basics
AI language models are not trained to give **the answer**. They are trained to give a **likely possible answer** that you as a researcher can then check using the evidence provided.
The quality of responses in the analysis grid or chat is heavily dependent on writing good prompts. Prompts *must* be **clear**, **detailed** and **specific**.
Below are some examples of this for the demo project (First time voters in the US).
## Things to try...
### Ask Specific Queries
The accuracy of the evidence retrieved for its answer will improve with more context so asking longer, more direct questions or clarifying what you are interested in with a follow-up will help.
| Good Example | Bad Example |
| :------------------------------------------------------------------- | :------------------------- |
| Summarise what voters said about their first time voting experience. | Summarise the main points. |
### Communicate in the imperative
CoLoop relies on language models that have been trained to follow instructions. Posing queries in an imperative mood, particularly when asking CoLoop to format or summarise previous conversations, will improve its performance.
| Good Example | Bad Example |
| :------------------------------------------ | :--------------------------------------------------- |
| Format the last message into bullet points. | Can you format your last message into bullet points? |
### Ensure your question contains specific language
CoLoop searches over its "memory" to find evidence to use when answering your query. More targeted language will increase the chance it will identify the right parts of the transcript to refer to.
| Good Example | Bad Example |
| :------------------------------------------------------------ | :------------------------------------ |
| What did participants say they like about concepts A, B and C | What did participants say they liked? |
### Ask qualitative questions in the AI chat
Update coming soon to allow you to ask quantitative questions..!
When using the AI chat be careful about asking quantitative questions. Current state-of-the-art language models cannot reason reliably about quantitative questions. If you want to know how many people mentioned something, use the Analysis Grid.
| Good Example | Bad Example |
| :----------- | :---------------------------------------------------------- |
| - | How many participants mentioned problems with registration? |
### Break up bigger or multi-step questions for better results
The example below isn't necessarily bad, but given the limited context, asking each part separately (e.g. "What are some of the pros of concept A?" followed by "What are some of the cons of concept A?") will result in a much more detailed answer.
| Good Example | Bad Example |
| :-------------------------------------- | :--------------------------------------- |
| What are some of the pros of concept A? | What are the pros and cons of concept A? |
### Provide sufficient context
If it isn't explicit in the transcript, you can help CoLoop by providing a bit of extra context. This is particularly useful for concept testing where people may be loosely referring to "A", "B" and "C", for instance.
| Good Example | Bad Example |
| :------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------- |
| Concepts A, B and C are examples of different advertising options. Which of these did the participants prefer? | What did participants think of the different options? |
### Use your imagination..!
LLMs and prompting are a rapidly evolving field. Lots of creative ideas for different prompts are being discovered every day by non-technical enthusiasts with a good intuition for how LLMs respond to inputs.
## Things to be careful of...
### Asking the AI to provide direct quotes
The underlying AI models are not constrained to quote directly from the text. If you ask them to "give me some quotes," it may not return verbatim quotes. To get verbatim quotes, click through on any of the generated text and use the quotes provided in the menu on the right-hand side.
# Analysis Grids
Source: https://docs.coloop.ai/docs/analysis/analysis-grids
Build an analysis grid: choose which participants or segments each row covers, ask questions as columns, read the overview across rows, and trace every answer back to the transcript.
An analysis grid turns your research material into a table you control. You decide what each row spans, what each column asks, and the type of output you'd like, and CoLoop generates the answers, with citations back to the source.
* **Rows** decide whose data an answer draws on — one participant, one segment, or a combination you build.
* **Columns** are the questions you ask. Each column has an output type, so every answer fits the question: synthesized analysis, verbatim quotes, an extracted number, a yes/no, or coded categories with counts.
* **Cells** hold one row's answer to one column's question.
* The **Overview** row at the top gives a summary of all rows' responses to each question.
## Create a grid
1. In your project sidebar, click **Analysis grid**.
2. Click the **+ Analysis grid** card.
3. Give the grid a name.
4. Choose how to set it up:
* **Custom grid** — build the grid from your project data. Pick where the rows come from (participants, segments, or an existing grid), then where the columns come from (your discussion guide, an existing grid, or skip to add your own questions).
* **Start from scratch** — create an empty grid and add the rows and columns yourself.
5. Click **Create grid**.
With a custom grid, CoLoop creates the grid and then prompts you to select the exact participants, segments, and questions you'd like in your grid. On your very first analysis grid, the [display setup](#change-how-the-grid-displays) comes first, and then you will be prompted to select your row and column setup once you've saved or skipped it.
A row or column source you can't use yet is grayed out: **From participants** and **From segments** require participants or segments in the project, **From discussion guide** requires a discussion guide, and **From existing grid** requires another grid in the project to copy from.
## Choose your rows
Each row carries a filter that decides whose data its answers come from. A row can be a single participant, a whole segment, or several of both combined.
### Add one row per participant or segment
1. Click **Add Participant Rows** in the grid header.
2. Stay on the **Add many** tab.
3. Search for participants and segments, and select the ones you want. Use **Add all** on a group heading to select everything in it, and **Clear all** to undo that.
4. Click **Add rows**.
Everything you select becomes its own row. CoLoop skips selections that duplicate a row already in the grid or that contain no participants, and tells you how many it skipped.
### Combine several participants or segments into one row
1. Click **Add Participant Rows** and open the **Build custom row** tab.
2. Select a segment or participant, then click **+** to add another.
3. Click the **AND** or **OR** between the entries to change how they combine.
4. Click **Add row**.
Use **OR** to expand a row so it covers everyone in either group. Use **AND** to narrow it down to only the participants who belong to every segment listed. **AND** only works with segments — a row that names a specific participant has to use **OR**.
Turn on **Create more** to keep the builder open so you can add several custom rows without reopening the dialog.
### Manage rows
* **Add a row inline** — use the **Add row** cell at the bottom of the participant column, which has the same builder as the dialog.
* **Reorder** — drag a row by the handle on its left edge. Remove any sorting first; rows can't be dragged while sorting is applied.
* **Edit** — hover over a row, open its three-dot menu, and click **Edit row** to change which participants and segments it covers.
* **Delete** — use **Delete row** in the same menu, or select several rows with their checkboxes and use **Delete** in the header bar.
* **Show segments** — each row lists the segments its participants belong to. Move them into their own column from the **Display** menu.
### Rows that lose a participant or segment
A row remembers the exact participants and segments you gave it. If one of them is later deleted from the project, the row labels it **Removed participant** or **Removed segment** in place of the name.
Two things commonly cause this:
* **Retranscribing a file.** Retranscribing replaces that file's speakers with new ones, so any row built on the old speakers no longer finds them.
* **Deleting a segment** that a row was built from.
A row that still covers someone keeps working, and its answers come from the participants that remain. A row that has lost everyone can't produce answers at all, and recomputing the grid won't bring them back — the data it pointed at is gone. To clear it:
1. Hover over the row and open its three-dot menu.
2. Click **Delete row**.
3. Add a new row for the participants or segments you want to analyze instead.
You can also use **Edit row** to drop the removed names and keep the rest of the row.
Grid exports carry the same labels, so a row that lost a participant reads the same way in your spreadsheet as it does on screen.
## Ask questions as columns
Each column is one question, asked of every row.
1. Click **Add a Question Column** at the bottom of the grid, or press **⌘K** (**Ctrl+K** on Windows).
2. Type your question.
3. Choose the output type, and add labels if you picked **Categorization**.
4. Press **Enter**, or click **Add column**.
CoLoop names the column from your question and starts computing straight away. The question composer stays open so you can add the next question immediately. Each column you add counts as one question against your plan's usage.
The column name is a short stand-in for your question. To read each question in full under its column title, turn on **Column questions** in the [display settings](#change-how-the-grid-displays).
### Output types
| Output type | What each cell returns | Use it for |
| ------------------ | --------------------------------------------- | -------------------------------------------------------------------- |
| **Synthesis** | A written answer with citations | Themes, summaries, reasoning, anything open-ended |
| **Quotes only** | Verbatim quotes from the participant | Pull-quote banks and quote sheets |
| **Numeric** | A single number, with an explanation | Ratings, prices, counts, ages |
| **Yes / No** | Yes, No, or Undetermined, with an explanation | Screening a behavior or an attitude across everyone |
| **Categorization** | Two or more labels you define | Coding responses against a codebook, participant counts per category |
A **Categorization** column needs at least two labels — the set CoLoop chooses from when it codes each row. Pick **Categorization** in the composer and the **Labels** row appears, where you can either:
* **Ask CoLoop for a starting set** — click **Suggest labels** and CoLoop drafts a set from your question. Write the question first: the button stays disabled until there's enough to work from.
* **Write your own** — click **Add your own**, then the **+** to add each label after that.
In both circumstances you will end up with a chip per label. Click a chip to rename it, remove it, or give it criteria describing when the label should apply — criteria are optional, but they sharpen the coding. Select **Mutually exclusive** when each row should get exactly one label.
Label names can't contain quotation marks, backslashes, or line breaks.
**Suggest labels** disappears once a label exists, so to re-draft a set, remove the labels you have. For a bigger codebook, open **Advanced**: the full editor lists each label with its criteria on its own line, and accepts a comma-separated or line-separated paste to add many at once — any pasted label with an unsupported character is skipped, and CoLoop tells you how many were left out.
### Narrow a column to specific data
Click **Add filter** in the composer menu to limit the question to certain files and concepts. Leave it empty to analyze all of the project data. This is per column, so one grid can hold a question about a single concept next to a question about several concepts.
Row filters and column filters do different jobs: row filters decide *whose* data is analyzed, and column filters decide *which of their data* is analyzed.
### Set a custom overview, or skip it
Click **Advanced** in the composer menu, or **Show advanced** in the add-column dialog, for the per-column overview controls:
* **Overview prompt** — replaces your question for the Overview row only. Use it to say what the summary across rows should answer and how it should be formatted. Leave it empty for the automatic thematic overview. Available on **Synthesis** columns only.
* **Skip overview** — leave the Overview cell empty for this column. Available on every output type, and off by default, so every column gets an Overview. On a **Quotes only** column the Overview is a synthesized thematic summary of the quotes across rows, while the per-row cells stay verbatim.
### Add columns from your discussion guide
Suggested questions come from the discussion guide you added during project setup. CoLoop intelligently groups these questions based on similar themes present in the guide.
Open the composer menu and, before you type anything, CoLoop lists suggested questions above the input. Click one to add it as a column, tick several and add them together, or click the pencil to load a question into the composer and change it first.
For the full selection of questions, click **Advanced**, then **Create from discussion guide**:
1. Choose questions from the **Suggested** tab, or from **Extracted** for the exact questions written in your discussion guide.
2. Click a question to review it on the right, and adjust its title, prompt, output type, labels, or filter before adding.
3. Every selected question will be added as a column.
To give a whole batch the same output type, set it on one question then click **Apply … to all selected**.
Questions that are already asked in columns are not suggested again. A question that can't be added as it stands — a categorization question with no labels, for example — is flagged so you can fix it first.
### Manage columns
Click a column header to open its menu:
* **Edit column** — change the question, output type, labels, filter, or overview settings. Editing recomputes the column.
* **Insert left** / **Insert right** — add a new column next to this one.
* **Duplicate column** — copy the question and its settings into a new column to tweak.
* **Delete column**.
Drag a column header to move the column, and drag its right edge to resize it.
## Read the results
Cells compute as soon as you add or edit a row or column, and recompute whenever you change something that affects them. You don't need to trigger anything.
While a grid is working, cells fill in as their answers land. Cells load as you scroll, so a large grid still opens quickly.
| Cell shows | What it means |
| ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| A loading placeholder | The answer is being computed |
| **Failed** with **Retry** | The cell couldn't be computed. **Retry** re-runs every failed cell in the grid |
| *No data to analyze. The current filters exclude all matching responses.* | Nothing was in scope for this cell. The column's file and concept filter and the row's participant or segment selection don't overlap, so there was nothing to read. Expand the column filter, or change what the row covers |
| **Undetermined** | A Yes/No column where the data doesn't answer the question either way |
| **No label** / **No labels** | A categorization column where none of your labels apply. A multi-label column shows this instead of the no-data message when a filter excluded everything, so check the column's filter before concluding your labels didn't fit |
| **Skipped** | An Overview cell for a column which skips its overview |
| **Not computed** | An Overview whose participants changed outside the grid, so no answer was ever built for the current set. Hover the cell and click **Compute grid** |
### The Overview row
The Overview row answers each column across every row in the grid. It appears once the grid has more than one row. When no row in a column had anything in scope, the Overview carries the same no-data message its cells do.
What you see depends on the output type:
* **Synthesis** columns get a thematic breakdown with the number of participants behind each theme — or your own summary if you set an overview prompt.
* **Numeric** columns get a single reduced value, such as an average or a total, with an explanation backing this value.
* **Yes / No** and **Categorization** columns get a distribution across participant of the count and percentage for each value.
#### When an Overview reads "Not computed"
An Overview answer covers an exact set of participants. Changes that happen **outside the grid** leave an Overview with no answer. Adding or removing a participant from a segment a row is built on, or a participant disappearing when their file is retranscribed, both move who the Overview covers. It then reads **Not computed**, rather than showing an answer that no longer matches the rows beneath it.
Hover the cell and click **Compute grid** to produce it.
That button computes the **whole grid**, not just the one Overview. It is the same action as **Compute grid** in the grid header, so it also picks up anything else outstanding — cells that never computed, or that failed.
### Look at one cell or one row in detail
Click any cell to open the details panel. It shows the row's filter, the full untruncated output, and — for Yes/No and categorization cells — the participant distribution. Click a bar in this distribution to see the individual participants' answers determining that value.
After selecting a cell, use the arrow keys to move to the next cell in that direction. The details panel follows your selection. If focus is on a control inside the cell, such as a citation, the arrow keys continue to control that item.
To read one participant's responses across every question, hover over their row and click **Open**. The row panel lists every column's answer for that row.
### Check the evidence
Every generated answer is cited. Click a citation to open the **Citation sources** panel, expand a quote to read it in context, click **Open** to jump into the transcript, or turn the quote into a clip.
For more on working with evidence and clips, see [Evidence Panels](/docs/analysis/evidence-panels) and [Creating Clips and Reels](/docs/analysis/creating-clips).
## Sort and filter what you see
Hover over a column header to reach its sort and filter icons, or add a rule from the bar above the grid.
* **Sort** — sort rows by any column, ascending or descending.
* **Filter** — filter by participant, by segment, or by the values in a **Yes / No** or **Categorization** column. Yes/No filters by Yes, No, or Undetermined; Categorization filters by label.
* **+ Filter** adds another rule, and **Reset** clears every rule.
Filtering needs a known set of values to pick from, so it's offered on **Yes / No** and **Categorization** columns only. **Synthesis**, **Quotes only**, and **Numeric** columns are sort-only: they have no filter icon and don't appear in the **+ Filter** menu. If you edit a column from Yes/No or Categorization into one of those types, any filter on it is dropped.
Sorting and filtering only change your own view of the grid. Nothing is saved to the grid or shown to collaborators.
### Overviews for a filtered view
A column overview summarizes every row, so it would misrepresent any filters applied. When a filter narrows the rows, the Overview row becomes **Filtered overview** and its cells read **Not computed** until you ask for them.
Click **Compute** on the Filtered overview row, or on an individual cell, to summarize exactly the rows you're looking at. Results are kept, so returning to the same filter shows the summary again without recomputing.
Some subsets can't be summarized, and the cell says why:
| Cell shows | What it means |
| -------------------------------- | ---------------------------------------------------------------------------- |
| **Too many rows to summarize** | Narrow the filter further |
| **A row failed - please retry** | A row's cell in that column failed. Retry it, then compute again |
| **These rows can't be combined** | The filtered set matches an existing row too closely to summarize separately |
## Recompute a grid
Grids recompute themselves as you edit them, so you rarely need to do this by hand. When you do — after a run of failures, for example — open the three-dot menu in the grid header and click **Compute grid**. CoLoop picks up anything that hasn't succeeded and leaves finished cells alone. If there's nothing outstanding, it tells you so.
**Retry** on any failed cell re-runs every failed cell in the grid, so you don't have to hunt them down one at a time.
## Change how the grid displays
Display preferences are saved to your account, so they will be set as the default on any device you use and apply to all grids in every project.
The first time you open an analysis grid, CoLoop allows you to choose these default display settings. **Welcome to Analysis Grids** presents each preference next to a mock grid that shows the change as you make it. Click **Save** to keep your choices, or **Skip for now** to start with CoLoop's default settings.
To change them later, open **Display** in the grid header. Editing a setting there applies immediately. For the descriptions and the mock grid, click **Display settings** at the top of that menu — choices in the panel are written when you click **Save**, and **Cancel** reverts whatever you changed.
| Preference | What it does |
| ------------------------------------ | ------------------------------------------------------------------------------------ |
| **Expand cells** | Show each answer in full instead of limiting it to the first few lines |
| **Show scrollbars** | Keep the grid scrollbars on screen rather than fading them in while scrolling |
| **Column questions** | Show each column's full question underneath its title |
| **Column previews** | While you're adding a question, outline where its column will land |
| **Quote context** | Show the researcher turn or task prompt above each quote in Quotes only columns |
| **Segments: Show as column** | Break segments out of the participant cell into their own pinned column |
| **Segments: Expand all** | Show every segment a row belongs to, instead of collapsing them |
| **Evidence panel: Expand citations** | Open each citation with its quoted text showing, rather than collapsed to the source |
### Fit more on screen
When a grid has many columns, three controls give you more room. These stay on the device you set them on rather than following your account.
* **Zoom**: scale the whole grid from 20% to 160% with the minus and plus buttons in the **Display** menu.
* **Full screen**: hide CoLoop's navigation so the grid fills the window. Click the header button again, or leave the grid, to bring it back.
* **Collapse the participant columns**: click the collapse arrow on the **Participants** header to fold the left columns into a thin rail. Click it again to expand.
## Export, rename, and share
Open the three-dot menu in the grid header for:
* **Export** — download the grid as an Excel file (XLSX), with a column of participants, their segments, the Overview row, and one column per question.
* **Manage access** — control who can see and edit the grid. See [Sharing analysis grids and AI chats](/docs/collab-and-access-management/sharing-analysis-grids-ai-chats).
* **Rename**.
* **Delete**.
You can also copy any cell or column out of the grid and paste it into Excel, Word, or a deck.
## Work across several grids
You can create as many grids as you like in one project — one per topic, workstream, or market for example. Click the grid name in the header to switch between them, and use **From existing grid** when creating a grid to reuse another grid's rows or columns as a starting point. A categorization column whose labels contain unsupported characters can't be copied — CoLoop leaves it out and counts it among the skipped columns.
## Coming from an older grid
Basic and comparative grids are now read-only. Open one and click **Clone to new grid** to copy its rows and columns into a new analysis grid, which then computes fresh with this updated format.
For the older grids themselves, see [Basic Grids](/docs/analysis/basic-grid) and [Comparative Grids](/docs/analysis/comparative-grids).
## Writing good questions
The question you write drives everything in the column. For prompting advice that applies across grids and chat, see [Top tips and prompting advice](/docs/analysis/top-tips-and-prompting-advice).
# Basic Grids
Source: https://docs.coloop.ai/docs/analysis/basic-grid
Reference for the legacy Basic Grids, which are now read-only. Covers how they work, what theme frequencies mean, and how to export them.
Basic grids are read-only. Open one and click **Clone to new grid** to copy its rows
and columns into an [analysis grid](/docs/analysis/analysis-grids), where you can
keep editing and asking questions.
* Basic analysis grids contain all of your participants.
* Each row corresponds to an individual speaker.
* They can be scoped to look at all the participants, IDI & Focus Group Participants or Participants from OBB / Communities like Recollective.
* They are limited to a maximum of 200 participants.
* They show a count next every theme corresponding to the number of participants the theme applies to.
## What you can still do
Open a basic grid from the Analysis Grids section to:
* Read every answer and the theme overview at the top of each column
* Click an answer to see the supporting quotes
* Copy a column, or export the whole grid
* Rename or delete the grid
* Clone it into a new analysis grid to continue the analysis
## What is no longer available
* Creating a basic grid
* Adding, editing, or regenerating a question
* Filtering a column by segment or concept
Columns left unfinished when grids became read-only show **Not generated** instead of an answer. Clone the grid into a new analysis grid to run those questions again.
## Cloning into an analysis grid
Click **Clone to new grid** to copy the grid's rows and columns into a new [analysis grid](/docs/analysis/analysis-grids), which then computes them in the current format. Every participant row carries across. If the same question appeared in two columns, the new grid keeps one, and tells you when it does.
## Understanding Theme Frequencies in the All Participant Grid
In the **All Participant Grid**, each column shows an overview of key themes based on the question you asked—and next to each theme, you'll see a **theme frequency** (a number). But what does that number actually mean?
Here's how it works:
1. **CoLoop first creates a summary for each participant**, based on all of their responses.
2. It then **reads across all participant summaries** to generate an overall theme overview for the column.
3. The **theme frequency** shows how many participants mentioned that theme in their summary for that specific question.
**Example**:\
If you ask *"What modes of transport did participants mention?"*, CoLoop will look at all the transport modes each person talked about. So if most people said things like "car, bus, plane," those will have **higher frequencies** because they were mentioned more often.
**But if you ask** *"What was each participant's favorite mode of transport?"*, CoLoop will only count the top or favorite mode each person gave. So the **theme frequencies will be lower**, since participants usually name just one favorite.
**Bottom line**:\
Theme counts depend on the question you ask—CoLoop summarizes each participant first, then builds the overview based on those summaries.
## Getting the supporting quotes
You can **click on any of the generated outputs** from the analysis grid **to see the supporting quotes**. The returned list of quotes will consist of the top x supporting quotes.

## Renaming a grid
Rename grids to keep things organized by clicking the 3 dots next to the page name.

## Exporting a grid
You can export a grid either by copying its columns and pasting them into an Excel sheet or Word document, or by exporting the entire table as an Excel sheet.
### Copying an entire column
These can be pasted into Excel, Word, Powerpoint and more.

### Exporting the entire table
Click on the three dots of the grid you would like to export. Exports from the table are in standard Excel format (XLSX).
Do this either when you're in the grid, by clicking on the three dots in the top right hand corner.

Or do this from the Analysis Grids section.

# Chat 1.0
Source: https://docs.coloop.ai/docs/analysis/chat-1.0
Reference for the legacy Chat 1.0, which is now read-only. Covers what you can still do with an existing chat and where to run new analysis.
Chat 1.0 is retired. Existing chats stay in your projects and remain readable, but you cannot start a new one or send further messages.
New chats now open in CoLoop's current chat. For the main analysis chat, see
[Thought Partner Chat](/docs/analysis/thought-partner-chat). For fast, quote-led
answers, choose **Quote finding chat** from the chat type menu.
## What you can still do
Open any existing Chat 1.0 from the Chats section to:
* Read the full conversation history
* Click a sentence in an answer to open the evidence panel and see the supporting quotes
* Click **Show working** on an answer to see the steps behind it
* Copy an answer
* Rename, share, pin, or delete the chat
## What is no longer available
* Creating a Chat 1.0
* Sending a message in an existing chat
* Regenerating an answer, or rating one up or down
* Resetting a chat's context
Opening a retired chat shows a notice in place of the message box with a link to the current chat.
## Moving your analysis across
Chat 1.0 conversations cannot be converted, because the current chat works differently: it plans its own retrieval on each run and cites every point back to the participants who made it. Re-ask your question in [Thought Partner Chat](/docs/analysis/thought-partner-chat) rather than copying the old prompt across, and use its **@** mentions or **Add filter** to set the scope you had filtered to before.
For guidance on phrasing, see [top tips and prompting advice](/docs/analysis/top-tips-and-prompting-advice).
# Chat 2.0
Source: https://docs.coloop.ai/docs/analysis/chat-2.0
Chat 2.0 is an upgraded chat feature that makes research analysis more systematic, reliable and focussed by combining structured grids with flexible chat-based synthesis. It adapts to your questions—using quantitative, conceptual, or thematic tools—to deliver insights with the most appropriate method.
## Introduction
Chat 2.0 is the updated chat feature designed to make research analysis more systematic, reliable, and easy to use. It combines the structured workflow of grids with the flexibility of chat-based synthesis.
Unlike the previous chat, Chat 2.0 is reactive: it adjusts the way it works depending on the question you ask. For example:
* If you ask a **quantitative question**, it uses quant analysis tools.
* If you ask a **conceptual question**, it uses concept testing tools.
* If you ask a **thematic question,** it uses thematic analysis tools.
This ensures that the response is not only relevant but also based on the most appropriate method.

## How to Use Chat 2.0
1. **Ask a Question**
* Be clear and specific. Chat 2.0 will select the right analysis approach based on your question.
* For complex, multi-step research queries, the Chat 2.0 will create a to-do list showing the steps it will take and ask you to confirm before proceeding.
2. **Review Artefacts**
* Chat 2.0 outputs artefacts—the answers to your questions.
* Every artefact includes **citations**, so you can check the supporting evidence.
3. **Use in Your Workflow**
* Incorporate artefacts into your analysis and reporting.
* Always review citations to ensure the findings are well supported.
## Best Practice Recommendations
* Use **Chat 2.0** when you need comprehensive synthesis, quant comparisons and adaptive responses.
* Use **Quote finding chat** for a quick, quote-led scan when you don't need structure.
* Always **review citations** before using artefacts in reporting.
* Think of Chat 2.0 as a **partner in structured analysis**—you guide with the questions, and it provides systematic evidence-based outputs.
### Examples of Prompts:
* **Thematic breakdowns**
* “Summarise the key themes in the data.”
* “Identify outliers in the data.”
* **Participant-level comparisons**
* “Find the similarities and differences between the Female and Male participants. Run two separate analyses.”
* **Concept and stimulus reactions**
* ”What did participants think about Concept A?”
* ”Breakdown perception of Concept A for segments X and Y”
* **Quantitative counts**
* “How many participants mentioned XX in their response?”
* “How many people knew about YY?”
* **Journey mapping**
* “Analyse participants’ decision-making in XX?”
* “What part of the process did participants find the most difficult?”
* **Segment-based analysis**
* “What are the key pain points per segment?”
* “What segments can you find in the data, aside from the ones I’ve already labelled?”
* **Evidence retrieval**
* “Find evidence supporting the hypothesis that participants thought XX about YY.”
* **Quote Retrieval**
* “Give me 2 quotes from every participant in segment Y”
* "Give me 1 quote from every female participant about what they liked about concept A"
* **Categorisation Question**
* "Break down the participants into part time and full time workers"
* "Break down the participants by the days of the week they work"
* **Comparative Analysis**
* "Compare and contract Segment A and Segment B on customer satisfaction"
* "What do engineers and designers have in common regarding work-life balance"
### **Additional Capabilities**
As well as texted based outputs, Chat 2.0 will also output thematic tables, numerical responses with proportion bars, sentiment tables for concept testing, and bar graphs and pie charts with data you can copy straight into excel.
**Thematic Analysis: Tables**
* Example Prompt: "What are the top 5 themes related to participant voting behaviours?"
**Qunatiative Queries: Numerical Outputs & Proportion Bars**
* Example Prompt: "How many participants said their families influenced their voting decisions?"
**Concept Testing: Sentiment Tables**
* Example Prompt: "Conduct concept analysis on #Novartis"
**Categorisation Questions: Bar Charts & Pie Charts with Copy-Ready Data**
* Example Prompt:
* Pie Chart (mutually exclusive): "Break down participants by part time and full time workers"
* Bar Chart (not mutually exclusive): "Break down the days of the week participants worked"
You can then click on the copy button (the overlapping box icon), and then paste the underlying data into excel to replicate the chart yourself.
**Comparative Questions: with strength scores across similarities and differences**
Ask for similarites, differences or both across segments across one variable. You'll get a table output with key similarities or differences per row, and a strength score which indicates the universality of the similairty or difference.
* Example prompts:
* For Similarities: "Find similarities between Segment A and Segment B on customer satisfaction"
* For Differences: "What are the differences between power users and casual users regarding feature requests?"
* For Both: "Compare and contrast Segment A and Segment B on product usability"
### Filtering in the Chat
Apply filters in the chat to limit the scope of your analysis. Filter by file, segment, participant, or concept. This is especially powerful for community and Excel files, where you can filter by specific questions or columns. Filtering helps you ask targeted questions and receive more relevant insights.
# Comparative Grids
Source: https://docs.coloop.ai/docs/analysis/comparative-grids
Reference for the legacy Comparative Analysis Grids, which are now read-only. Covers how their custom segment and participant rows work.
Comparative grids are read-only. Open one and click **Clone to new grid** to copy its
rows and columns into an [analysis grid](/docs/analysis/analysis-grids), where you can
build the same custom rows and keep editing.
Comparative Analysis Grids, previously called Custom Grids, group participants into custom rows by segment and participant. Each row summarizes how that group responded to the question at the top of the column, which makes them useful for consolidating a large number of participants into a readable grid.
## What you can still do
Open a comparative grid from the Analysis Grids section to:
* Read every row's summary and the overview at the top of each column
* Click any bullet point to see which participants were bucketed into it, and hover a participant name to check their segments
* Click an answer to see the supporting quotes
* Copy a column, or export the whole grid
* Reorder or delete columns, and rename or delete the grid
* Clone it into a new analysis grid to continue the analysis
## What is no longer available
* Creating a comparative grid
* Adding a row, or editing a row's segment and participant filters
* Adding, editing, or regenerating a question
Rows and columns left unfinished when grids became read-only show **Not generated** instead of an answer. Clone the grid into a new analysis grid to run those questions again.
## Cloning into an analysis grid
Click **Clone to new grid** to copy the grid's rows and columns into a new [analysis grid](/docs/analysis/analysis-grids), which then computes them in the current format.
Two things can change during the copy, and CoLoop tells you how many when it happens:
* **Rows whose filter no longer matches anyone are skipped.** A row built on a deleted participant or an emptied segment resolves to nobody, so it is dropped rather than copied empty.
* **Duplicate rows and columns are merged.** If two rows or two questions were identical, the new grid keeps one.
Check the new grid against the original before you rely on it, and rebuild any skipped rows from the segments you still have.
## Row filters
Each row was built from a filter combining up to 10 segments and 50 speakers. Open a row's filter to read how it was composed, including the conjunction used to combine its parts. The filter is displayed for reference and can no longer be edited.
For larger datasets, such as community data with more than 200 participants, use an [analysis grid](/docs/analysis/analysis-grids).
# Content Analysis Reports
Source: https://docs.coloop.ai/docs/analysis/content-analysis-reports
Learn about and how to use content analysis reports. See granular breakdowns of your findings by discussion guide question and participant segments.
Content Analysis provides structured, question-by-question insights and illustrative quotes, organized directly under your discussion-guide questions.
Additionally, project members can subscribe to grids and receive email updates when new interviews are added. This allows users to get full content analysis in real time as the project progresses.

### How to use Content Analysis Grids
**Set Up Project**
1. Create the project and make sure to upload the discussion guide.
2. Upload files (at least one). Content analysis grids will work with video, audio and transcript files only.
**Create Content Analysis**
3. Navigate to Analysis Grids in the left hand menu, and then to + Create New Grid in the top right hand corner of the grid page. Then, select 'Content Analysis Report'.
**Assemble Report Questions**
4. Build your framework by either selecting ‘Initialize with AI’ (recommended), which will pull the questions from the discussion guide uploaded during project set up, or ‘Add Questions Manually’.
5. CoLoop will automatically group probes/sub-questions under their related parent questions. Additionally users can drag and drop to reassign probes, reorder questions and edit question text if required.

6. When complete, press start. It is not possible to go back and edit discussion guide question structure after this.
7. CoLoop may take a few moments to generate analysis.
**Explore the Analysis View**
8. The analysis view has two sections you click between in the top left of the screen, the overview section and the quotes section.

**Overview Section**: Click any dropdown next to a question to open its analysis. Under each question users will find a table with relevant research objectives and underneath that a content analysis grid.
* **Research objectives:** these are the objectives you confirmed during your project setup. CoLoop shows which research objectives link to each question. These can be toggled off for a cleaner view by clicking display in the top right hand corner.
* **Content analysis tables**: A top-level theme summarizing participants’ primary response pattern, sub-themes breaking down nuances and variations and a brief summary for quick interpretation. Participant names and their associated segments are display next to each point and clearly color-coded for easy visual scanning. Users can click on the themes or sub-level themes to open up the evidence panel.
**Quotes Section**: Click on any dropdown next to a question to see associated quotes from each participant, in relation to the selected discussion-guide question.
9. Use filters to breakdown analysis further. Users can filter by segment, individual participant or a combination of both. Filters apply to both the overview and the quotes sections.
10. Use the share button at the top right hand corner to add colleagues to the project. Users can subscribe to a project to keep track of how insights evolve in real time as files are added to the project.
11. Finally users can export the content analysis by clicking on the three dots in the top right hand corner to export as an excel, or the copy button next to each question.
**Sharing with colleagues and real-time updates**
12. Subscribe yourself, project members or other colleagues to the content analysis grids. They'll receive real-time updates when new interviews are added.
13. Users can choose to receive updates daily, once every three days or once a week. Manage notifications by clicking on the notifications button on the left hand menu.

### Supported data
Content analysis reports use interview files only. They do not include community data.
### FAQs:
**What if the questions in my interview are worded differently to how the questions are written in my discussion guide?**
CoLoop will correctly find the section of the transcript with the closest relevant meaning.
**What if the question order is randomized?**
CoLoop finds the correct section of the transcript based on the meaning of the question and not on the order it’s presented in.
# Creating Clips and Reels
Source: https://docs.coloop.ai/docs/analysis/creating-clips
Learn how to generate audio and video clips directly from transcripts using CoLoop. Stitch audio and video clips together across all project files into a single, shareable, reel and export them for sharing. Clips and reels are an easy way to incorporate authentic participant voices into strong deliverables, presentations, and narratives.
CoLoop supports audio and video clip generation directly from transcripts. Find all your clips in two dedicated sections within each project: file-specific clips appear on the right-hand side of the file view, while all clips from all uploaded files can be found in the **Clips & reels** section in the left-hand sidebar. This makes it easy to browse, play back, and download multiple clips at once.

## How do I create a clip?
1. **Open a transcript** within your project.
2. **Select** the text you’d like to turn into a clip.
3. Click '**Create Clip**.'
4. Confirm by selecting **‘Create Clip’** again in the bottom right corner of the video.
5. A message confirms the clip is being created. Click **Clips & reels** in the message to go straight to the **Clips & reels** section of your project. The clip appears there right away, marked **Processing** until it is ready to play.
6. From the **Clips & reels** section, you can:
* **Play back** clips instantly.
* **Navigate** back to the original transcript using the provided shortcut.
* **Download** clips individually or in batches.
Downloads use the name you give your clip. CoLoop shortens long download filenames while keeping the file extension; your clip's name in CoLoop stays unchanged.



## How to Make Reels
To find all clips within an entire project, navigate to the **Clips & reels** library in the main left-hand sidebar.
1. To create a reel, click **+ New Reel** at the top of the screen. If you have no existing reels, click **Create Video Reel** instead. CoLoop opens a new untitled reel in the editor.

2. To add clips to your reel, click ‘Add to reel’, and that clip will appear in the timeline underneath the main video frame. You can drag clips around in the timeline to reorder. You can use any clips you’ve created in a project.
3. On the right hand side, search for key words or filter by segment or participant to bring up specific clips. With large datasets, it can be helpful to toggle participant names and segments on.
Filtering and searching for clips helps create videos covering specific topics or segments easily.

4. To add context or preamble between clips in a reel, hover over the timeline and click the **+** button at any point, including before the first clip or after the last. Choose **Text** to show a title card (for example, a theme name or research question) on a black background, or **Image** to upload a PNG, JPEG, or WebP (up to 5MB, at most 4000px per side). Set how long the card holds on screen (up to 60 seconds), then click **Add card** (or press **⌘↵**, **Ctrl+Enter** on Windows). Cards appear in the timeline like clips: drag to reorder, or hover over one to edit or remove it. Cards render into the exported video exactly as shown in the preview, and stay sharp even when the video is blurred. Reels made only of audio clips normally export as audio files; adding a card (or burning subtitles) turns the export into a video, with audio clips shown as black frames.
5. Open **Effects** and select **Blur entire video** to obscure the full video frame in the exported reel. The editor shows an approximate preview. The final, non-reversible blur is applied during export. The **Effects** menu is available while a reel has unexported changes; for an already exported reel, click **Edit** first.
6. To blur only part of a clip, like a face or a screen, hover the clip in the timeline and click the shield icon (**Blur sections**). Draw one or more rectangles over the video, then save. The blur is baked into those regions of the exported reel and cannot be reversed in the export itself; the source video and clip are not modified. Clips with blurred regions show a shield badge in the timeline. To change or remove the blur, reopen **Blur sections**, adjust or clear the rectangles, and export the reel again.
7. Open **Effects** and select **Modulate voices** to disguise every voice in the exported reel. The export pitch-shifts the audio by a random amount fixed for that reel, so re-exports sound the same and the original voices cannot be recovered from the download. Combine it with a blur to hide both face and voice. It applies to audio-only reels too. The editor preview plays the original audio, so **Voices modulated on export** appears next to the **Effects** menu as a reminder of what the download will sound like.
8. Turn on **Subtitles** via the bottom right corner of the reel before exporting to burn subtitles onto the downloaded video. Click the translation icon next to the subtitle icon to choose the original language or an available translation, such as English. If you edit the transcript later, export the reel again to update the subtitles.
9. Open **Effects** and select **Clip labels** to burn a small label over each clip in the exported video. Choose any combination of the clip's name (falling back to its file name), the names of the participants in the clip, and the segments of those participants (each on its own line), and pick which corner of the frame the label appears in. Clips with nothing to show (for example, speakers without segments) skip that line or are left unlabeled. Labels reflect each clip's trimmed range: participants and segments you trim out of a clip are dropped from its label, and the same clip added twice with different trims can show different labels. While editing, the reel preview shows the label in place so you can check the content and corner before exporting. If you rename clips, change participants or segments, or adjust trims later, export the reel again to update the labels. Cards are not labeled.
10. Click **Export**.
11. When the export completes, download the finished reel from the editor or clip library.
All reels remain available in the clip library. Draft reels must be exported before you can download or share them. Open the three-dot menu under a reel to edit, rename, download, or delete it.

## How to share a reel
Sharing a reel creates a public link. Anyone with the link can watch and download the reel without a CoLoop account. They cannot see your project, transcripts, or any other clips.
A reel must be exported before you can share it. If you have changed the reel since its last export, export it again first.
1. Click **Share** — the button sits under every reel in the clip library and in the top-right corner of the reel editor.
2. Select **Create public link**.
3. Copy the link and send it to whoever needs it.
### Embedding a reel
The share dialog has two tabs:
* **Link** — send this link to anyone; they can watch and download the reel in their browser. You can also paste it into Notion to embed the player, or add it to a Google Doc as a clickable link.
* **iframe** — paste this iframe anywhere that accepts HTML, such as reports, dashboards, client portals, or company websites, to play the reel inline.
PowerPoint and Google Slides do not support embedded videos.
To revoke access, click **Share** and select **Stop sharing** (also available in the reel's three-dot menu). The link stops working immediately and cannot be reactivated — sharing again creates a new link.
### When a shared link pauses
A public link only serves the version of the reel you last exported. If the reel goes out of date (you edit its timeline, change an export option, or blur one of its source videos), the link stops working and the reel shows a **Public (paused)** badge in the clip library.
Anyone opening a paused link sees a "not found" page. The link is not revoked, only paused: export the reel again and the same link starts working, now serving the updated version.
Because exporting a paused reel republishes its existing link, select **Stop
sharing reel** if you want access revoked for good.
### Sharing reels made from blurred videos
[Blurring a video](/docs/file-formats/video-audio#video-blurring) is permanent: the blurred version becomes the only one served anywhere in CoLoop. Clips and reels made before the blur were cut from the unblurred video, so CoLoop withholds them until they have been rebuilt from the blurred version:
* **While the blurring runs**, the reel's public link returns "not found," and you cannot export or download the reel.
* **Once the blurring completes**, the reel is marked out of date and its link stays paused. Clips are re-rendered from the blurred video automatically and cannot be downloaded until that finishes.
* **Export the reel again** to rebuild it from the blurred video. Its public link then resumes on its own, serving the blurred version.
If a reel draws on several videos, blurring any one of them pauses the reel.
## Recommended use
Clip reels are great for boosting your deck and narrative with real voices from your participants.
**Top Tip:** Use the chat feature to pull relevant quotes—a quick way to find great clips without combing through transcripts. When you open the evidence panel on a result, click **Clip** on any quote from an audio or video file to create a clip in one step. See [Evidence Panels](/docs/analysis/evidence-panels).
# Evidence Panels
Source: https://docs.coloop.ai/docs/analysis/evidence-panels
This document will walk you through evidence panels in CoLoop. Every piece of analysis in CoLoop is fully cited—just click on a theme, insight, or quote, and you'll see the exact evidence the tool used to generate it. It's a transparent way to trace insights back to the original data.
The evidence panels in the analysis grids and AI chat establish a hypothesis-led approach as you can **always** have the link back to the sources to see if you agree with the suggestions the AI is providing.
Use the evidence panel to dig into the detail behind every insight.
* Click summaries, themes, or quotes to see the exact supporting evidence.
* All sources are cited and linked back to the original transcript.
* Stay grounded in the data and easily verify findings.
You can **click on any of the generated outputs** from the analysis grid **to see the supporting quotes**. The returned list of quotes will consist of the top x supporting quotes.

From the evidence panel you can click 'Open' to open up the transcript and go directly to the context.


## Create a clip from a quote
When a supporting quote comes from an audio or video file, you can turn it into a clip without leaving the evidence panel.
1. Click a supporting quote to expand it.
2. Click **Clip**.
CoLoop creates a clip of that quote and confirms with a message. Click **Clips & reels** in the message to go straight to the project's **Clips & reels** section. The clip appears there right away, marked **Processing** until it is ready to play.
If you don't see **Clip**, the quote comes from a file that has no audio or video to clip.

To play back, download, or combine clips into a reel, see [Creating Clips and Reels](/docs/analysis/creating-clips).
# Skills
Source: https://docs.coloop.ai/docs/analysis/skills
Skills are reusable prompt templates that guide how the Thought Partner chat responds. Create personal skills, publish them across your project or organization, and manage organization-wide skills as an admin.
## What are Skills?
Skills are saved prompt templates that customize how the Thought Partner chat analyzes your data. Instead of rewriting complex instructions each time, you can create a skill once and reuse it across chats and projects.
The CoLoop team creates and maintains a library of high-quality qualitative research skills across a variety of domains, available to all users out of the box.
You can access skills via the **Explore Skills** dialog in the project sidebar.
## Skill Scopes
Skills exist at four levels. What you can see and do depends on your role and where the skill was created.
| Scope | Visible to | Who can create | Who can delete |
| ---------------- | --------------------- | --------------------------------------------------------------- | ---------------------------------------- |
| **CoLoop** | Everyone | Managed by CoLoop | Managed by CoLoop |
| **Organization** | All workspace members | Organization admins (directly or by approving publish requests) | Organization admins |
| **Project** | All project members | Any project member | The skill creator or organization admins |
| **Personal** | Only you | Any user | The creator |
## Creating a Skill
1. Open a project and click **Explore Skills** in the sidebar.
2. Select the **Personal** tab and click **New Skill**.
3. Give the skill a name, optional description, and write the instructions for the skill.
4. Click **Save**.
The skill is now available in your personal skill list across all your projects.
## Publishing Skills
You can publish a personal skill to a broader audience:
* **Publish to Project** — copies the skill to the current project so all project members can use it.
* **Publish to Organization** (admin only) — copies the skill so everyone in your workspace can use it.
* **Request Publish to Organization** (non-admin) — sends a request for an organization admin to review and approve.
After publishing, your original personal skill remains unchanged. The published copy is independent.
## Managing Organization Skill Requests
If you're an organization admin, you will see a wand icon in the top bar of your workspace. Clicking it opens the **Organization Skill Requests** dialog where you can review pending publish requests from your team.
For each request you can:
* Expand the row to preview the full skill instructions.
* **Approve** — the skill becomes available to everyone in your workspace.
* **Reject** — optionally provide a reason. The requester's original skill is not affected.
To browse, edit, or delete all organization skills, open **Explore Skills** from any project and select the **Organization** tab.
## Enabling and Disabling Skills
You can toggle skills on or off from the Explore Skills dialog. Disabling a skill hides it from your skill picker without deleting it.
## Admin Skill Management
Organization admins with internal admin access can manage built-in skills from the admin panel under **Skills**. This allows creating, editing, and deleting system-wide built-in skills.
# Thought Partner Chat
Source: https://docs.coloop.ai/docs/analysis/thought-partner-chat
The Thought Partner chat is CoLoop's main analysis chat — an AI research agent that interrogates your interviews and turns them into cited, flexible outputs. How to use it, focus it, and get the best results.
## Introduction
Use the Thought Partner chat to explore themes, compare groups, drill into specific points, quantify what you find, and write up the result — all in one conversation, with every point grounded in the participants who said it.
## How to Use Thought Partner Chat
Ask your question in plain language and the chat works through your interviews to answer it. It keeps the conversation's context, so you can refine with follow-up questions rather than starting over.
### Focus the data
The chat picks the relevant data on every run, interpreting your question to choose the participants, segments, or concepts it needs. You can steer that, or lock it down, in two ways:
* **Mentions.** Type **@** to insert a participant or segment, or **#** to insert a concept you've tagged. The chat then works from only that tagged subset.
* **A fixed scope.** Set a manual scope with **Add filter**: all following messages then use only your selected files, participants, segments, and concepts. The chat can narrow further within that scope, but never reach outside it, until you change it.
Check what the chat is using on each run. If it's working from the wrong set, rephrase your question or set the scope manually.
### Check the evidence
Every claim in the chat is backed by evidence, so you can always trace an insight back to the participants who said it and decide whether you agree.
Each claim is followed by a citation showing how many participants support it.
Click the citation — or any claim, theme, or quote — to open the evidence panel, which shows:
* Which participants were cited for that claim.
* Why each was selected: the reason that participant supports the point.
* Their exact words: the supporting quotes, pulled straight from the transcript.
To go deeper, click "Open" on any quote to jump to that turn in the full transcript and read the surrounding context.
### Compare groups
Ask the chat to compare segments or individuals directly — for example, "Compare how Amazon, Uber, and Lyft drivers feel about their pay." It builds a separate filter for each group, analyzes each one on its own, and combines them into a single comparison at the end.
Name each group with an **@** mention so the chat scopes it correctly, then glance at the filters it created to confirm each has the right participants before you read the result.
### Add files for extra context
You can attach images and files (PDF, Word, PowerPoint, or text) to a message for extra context, or ask the chat to confirm or validate their content. Attachments apply to the message you send them with — the AI reads them as part of that question. They're background context, not part of your cited dataset; your project files remain the basis of the research.
See [Adding files & images to chat](/docs/analysis/uploading-files-to-chat) for full limits and handling.
### Use skills
Skills are saved prompt templates that customize how the Thought Partner chat analyzes your data. Instead of rewriting complex instructions each time, create a skill once and reuse it across chats and projects. CoLoop also maintains a built-in library of qualitative research skills available to everyone.
See the [Skills](/docs/analysis/skills) page for more.
## Tips to get the best results
### Use the suggested prompts
A new chat suggests prompts tailored to your project. Click the category chips under the chat box to browse them by goal.
### Be specific in your prompts
The strongest prompts name the analysis you want, say how to break it down (by segment, participant, or concept), and ask for quotes and citations. For detailed example prompts grouped by goal, see [Top Tips and Prompting Advice](/docs/analysis/top-tips-and-prompting-advice#detailed-example-prompts).
***
Data: Enriquez, Diana, "Delivery Gig Worker Interviews on Automation at Work" (2019), [https://doi.org/10.34770/4324-yn77](https://doi.org/10.34770/4324-yn77). Licensed under CC BY 4.0. Analyzed/processed for demonstration purposes.
# Top Tips and Prompting Advice
Source: https://docs.coloop.ai/docs/analysis/top-tips-and-prompting-advice
This guide will walk you through when to use Grids versus the AI Chat in CoLoop, helping you choose the right tool for different stages of your analysis. You’ll also find top tips for prompting the AI effectively to get richer, more targeted insights.
* [Top Tips Overview ](/docs/analysis/top-tips-and-prompting-advice#top-tips-overview)
* [When to Use the Grids versus the Chat ](/docs/analysis/top-tips-and-prompting-advice#when-to-use-the-grids-versus-the-chat)
* [Prompting Dos and Don'ts ](/docs/analysis/top-tips-and-prompting-advice#prompting-dos-and-don%E2%80%99ts)
* [Prompting Practical Tips](/docs/analysis/top-tips-and-prompting-advice#prompting-practical-tips)
### Top Tips Overview
### When to Use the Grids versus the Chat
| Analysis Grid | AI Chat |
| :---------------------------------------------------------- | :---------------------------------------------------------------------------- |
| Open analysis: “I’m not sure what I’m looking for just yet” | Closed analysis: “I know what sorts of things I’m trying to find or validate” |
| Good for exploring themes | Good for finding specific quotes / generating summaries |
| Based on one piece of evidence for every participant | Based on top N pieces of evidence |
| Can’t ask follow up questions | Can ask follow up questions |
### Prompting Dos and Don'ts
✅ **Rephrase your question:** Just like with Google — if you don’t find what you’re looking for the first time, try asking differently.
✅ **Ask specific questions:** CoLoop uses your prompt and project description to find answers. If it’s unclear what to look up, the answer won’t be helpful.
✅ **Ask simpler questions:** CoLoop considers one thing at a time. If you ask three questions at once, the response will be less detailed than if you asked them one by one.
❌ **Don’t ask quantitative questions:** The AI chat isn’t reliable for “how many” or “how much” questions — use the analysis grid instead.
✅ **Always check the full evidence panel:** The quote you’re looking for might not be at the top — scroll to review everything.
✅ **Use filters when possible:** Segment filters reduce the amount of data CoLoop processes and improve accuracy.
✅ **Reset the chat:** When changing topics, reset the chat to avoid carryover from earlier questions.
### Prompting Practical Tips
| Guidance | Example |
| :--------------------------- | :------------------------------------------------------------------------------------------------ |
| Be Specific | What are good quotes to support the idea that participants found the packaging difficult to open? |
| Break up complicated prompts | What are the main advantages of concept A? |
| Provide Examples | Find me some similar quotes to this one “ “ |
| Use Quotes | Did anyone mention “Product X” in their responses |
| Use Segments | What are some quotes from @non-users to support the idea that … |
| Tell CoLoop how to answer | What are some of the main concerns participants expressed? Answer in a bulleted list. |
| Give CoLoop feedback | Improve your last response by adding more detail about X |
### Detailed Example Prompts
For more involved analyses, here are detailed, ready-to-adapt prompts grouped by goal. Swap the placeholders — like `[topic]` or `Segment A/B` — for your own study.
**Segment comparison**
* Compare Segment A and B's top concerns. List each segment's top 3–5 with quotes, then highlight where they diverge most.
* Compare first reactions to Concept A vs B — emotional response, language used, and objections raised.
**Contradictions and conflict**
* Find where participants contradict themselves. Quote both statements, note the context shift, and what it reveals.
* Find topics where participants disagree. Group opposing camps with quotes and the underlying assumption driving each.
**Surprises and outliers**
* Surface the 5 most surprising or counterintuitive findings. Explain why each is surprising with supporting evidence.
* Identify outlier participants. Summarize their view and assess whether it's fringe or an early signal.
**Language and emotion**
* Identify recurring metaphors and phrases used to describe \[topic]. Group by theme, note which recur vs one-offs.
* Map emotional intensity across topics. Which spark strong emotion vs neutral mentions? Quote the strongest moments.
* Run a rigorous qualitative analysis: top themes with frequency, key tensions, segment differences, and gaps. Quote and cite for each.
* Run a JTBD analysis. For each job: functional, emotional, social; trigger; current alternatives; success criteria. Rank by frequency and intensity.
* Run a thematic analysis. Produce themes → sub-themes with counts, quotes, and business meaning. Flag thin themes.
* Build personas from this data. Each with behaviors, goals, frustrations, drivers, language, anchor quotes, and source participant IDs.
* Run a decision-driver analysis for \[key decision]. Separate stated reasons from revealed reasons where they diverge.
* Run a journey analysis for \[process]. Map stages, emotional highs/lows, friction points, and where journeys diverge by segment.
* Identify the strongest new market opportunity. Specify segment, unmet need, why now, evidence strength, and key risks.
* Suggest 3–5 product or feature opportunities. For each: unmet need, affected segments, evidence strength, impact vs effort.
* Suggest 2–3 positioning directions based on participants' language and emotional drivers. Include target segment and supporting quotes.
* Recommend which segments to prioritize vs deprioritize, based on signal strength, intensity of need, and willingness to act.
* What follow-up research is needed? Identify questions raised but unanswered, plus sample or methodological gaps.
* Pressure-test \[hypothesis]: evidence for, evidence against, what's missing, and a confidence verdict (strong/mixed/weak/contradicted).
* Find the strongest counter-arguments to \[finding]. Quote participants whose views complicate it and explain a skeptic's read.
* Does the data support \[new idea]? Identify evidence for/against, segments most/least likely to respond, and untestable assumptions.
* Stress-test for sample bias. What users, contexts, or viewpoints are under-represented, and how might that skew conclusions?
* What evidence would disconfirm my hypothesis that \[X]? Specify what future research would need to show.
* Write a compelling narrative for \[key finding]: hook, finding, why it matters, 4–6 supporting quotes, nuance, implications.
* Write a one-page executive summary: top 3 findings, implications, next steps. Assume the reader has 2 minutes.
* Reframe \[key finding] for \[audience: product/marketing/leadership]. Adjust emphasis, language, and the "so what."
* Pull 10–15 of the most powerful verbatim quotes. One line of context each, tagged by theme.
* Show the full evidence base for \[claim]: every supporting quote, every contradicting quote, with participant IDs, then a verdict.
* How many participants raised \[topic], in what context, with what intensity? Separate unprompted mentions from prompted ones.
* Audit \[previous summary or finding] against the raw data. Flag overstated, under-evidenced, or unsupported claims.
# Adding Files & Images to Chat
Source: https://docs.coloop.ai/docs/analysis/uploading-files-to-chat
Attach images, PDFs, Word, PowerPoint, and text files to a chat to bring extra context into your analysis, plus the supported formats, size limits, and how each file type is handled.
You can attach files and images directly to a [Thought Partner chat](/docs/analysis/thought-partner-chat). Use this to give the AI extra context alongside your project data, such as a discussion guide, a stimulus image, a slide deck, or a brief.
Attachments apply to the message you send them with. The AI reads them as part of that question.
## How to add a file or image
You can add a new file in three ways:
* **Click the paperclip** icon in the chat input, then click **Upload from device**.
* **Drag and drop** one or more files anywhere onto the chat.
* **Paste** an image or file you have copied to your clipboard.
You can attach **up to 4 files per message**. Add a message describing what you want the AI to do with the files, then send.
When you drag a file over the page, a **Drop file to attach** overlay appears. Release the file anywhere on the chat to attach it. Attached files then appear as previews above the message input, where you can remove any you added by mistake before sending.
## Reuse a file you uploaded before
1. Click the **paperclip** icon.
2. Select one of your three most recent files, or click **Browse uploaded files**.
3. To find an older file, search by file name.
The list contains files you previously sent in a chat in this project. You only see files that you uploaded; files uploaded by other project members do not appear. You can reuse the same file in multiple chats.
## Supported file types and limits
| File type | Extensions | Max size | Other limits |
| -------------- | ----------------------- | -------- | -------------------------------------------------------------------------- |
| **Images** | `.jpg`, `.png`, `.webp` | 5 MB | Up to 2000px on the longest side (larger images are resized automatically) |
| **PDF** | `.pdf` | 50 MB | Up to 1,000 pages |
| **Word** | `.docx` | 30 MB | Text only (images are not read); up to 800,000 characters |
| **PowerPoint** | `.pptx` | 25 MB | Up to 1,000 slides |
| **Text** | `.txt` | 1 MB | Up to 800,000 characters |
If a file is the wrong type or over a limit, CoLoop tells you when you try to attach it and skips that file.
## How your files are handled
**Images are resized automatically.** If an image is larger than 2000px on its longest side or over the 5 MB limit, CoLoop resizes it before sending so you rarely need to worry about size. If an image is still too large after resizing, upload a smaller version.
**PowerPoint is converted to a PDF.** When you attach a `.pptx` file, CoLoop converts it to a PDF so the AI can read each slide visually, including charts, images, and layout. This happens automatically after upload.
**Word files are read as text only.** For `.docx` files, the AI reads the text content. Images, charts, and other visuals embedded in the document are not recognized.
Word documents are the exception: their visuals are not read. If a `.docx` relies on charts or images, save it as a PDF or attach those visuals as separate images so the AI can see them. PowerPoint files do not need this — they are converted to PDF automatically.
# Topline Summaries
Source: https://docs.coloop.ai/docs/analysis/writing-a-good-topline
Learn how CoLoop automatically generates topline summaries for uploaded interviews. Export summaries effortlessly from the transcript view to streamline qualitative research analysis.
CoLoop will generate a summary of every interview you upload. The summary is guided by the [project description](/ai-skills-hub/advanced-analysis/writing-good-proj-desc). Summaries are available in the transcript view.
## Exporting the summary
You can export the summary at any point by clicking the 3 dot menu in the transcript view:
# OAuth Flow
Source: https://docs.coloop.ai/docs/api/authentication/flow
The authentication flow differs based on whether you're using a private or public application.
## Private Application Flow (Authorization Code)
1. **Redirect Users to Authorization URL**
Construct the authorization URL with your `client_id` and `callback_url`:
```javascript theme={null}
const authUrl = new URL("https://clerk.coloop.ai/oauth/authorize");
authUrl.searchParams.append("client_id", "your_client_id");
authUrl.searchParams.append("redirect_uri", "your_callback_url");
authUrl.searchParams.append("response_type", "code");
authUrl.searchParams.append("scope", "email profile");
// Redirect user to authUrl
```
2. **Handle the Callback**
After authorization, CoLoop redirects to your callback URL with an authorization code:
```javascript theme={null}
// Example callback URL:
// https://your-domain.com/oauth2/callback?code=abc123...
```
3. **Exchange Code for Tokens**
Make a POST request to the token endpoint:
```javascript theme={null}
const response = await fetch("https://clerk.coloop.ai/oauth/token", {
method: "POST",
headers: {
"Content-Type": "application/x-www-form-urlencoded",
},
body: new URLSearchParams({
grant_type: "authorization_code",
client_id: "your_client_id",
client_secret: "your_client_secret",
code: "authorization_code_from_callback",
redirect_uri: "your_callback_url"
})
});
const tokens = await response.json();
// {
// "access_token": "...",
// "refresh_token": "...",
// "scope": "email profile",
// "token_type": "bearer",
// "expires_in": 7200
// }
```
## Public Application Flow (PKCE)
1. **Generate PKCE Challenge**
```javascript theme={null}
// Generate a random code verifier
function generateCodeVerifier() {
const array = new Uint8Array(32);
crypto.getRandomValues(array);
return base64UrlEncode(array);
}
// Create code challenge
async function generateCodeChallenge(verifier) {
const encoder = new TextEncoder();
const data = encoder.encode(verifier);
const digest = await crypto.subtle.digest("SHA-256", data);
return base64UrlEncode(new Uint8Array(digest));
}
const codeVerifier = generateCodeVerifier();
const codeChallenge = await generateCodeChallenge(codeVerifier);
```
2. **Redirect to Authorization URL with PKCE**
```javascript theme={null}
const authUrl = new URL("https://clerk.coloop.ai/oauth/authorize");
authUrl.searchParams.append("client_id", "your_client_id");
authUrl.searchParams.append("redirect_uri", "your_callback_url");
authUrl.searchParams.append("response_type", "code");
authUrl.searchParams.append("scope", "email profile");
authUrl.searchParams.append("code_challenge", codeChallenge);
authUrl.searchParams.append("code_challenge_method", "S256");
// Redirect user to authUrl
```
3. **Exchange Code for Tokens**
```javascript theme={null}
const response = await fetch("https://clerk.coloop.ai/oauth/token", {
method: "POST",
headers: {
"Content-Type": "application/x-www-form-urlencoded",
},
body: new URLSearchParams({
grant_type: "authorization_code",
client_id: "your_client_id",
code: "authorization_code_from_callback",
code_verifier: codeVerifier,
redirect_uri: "your_callback_url"
})
});
const tokens = await response.json();
```
#### Using the Access Token
For both flows, use the access token to make authenticated requests:
```javascript theme={null}
const userInfo = await fetch("https://clerk.coloop.ai/oauth/userinfo", {
headers: {
"Authorization": `Bearer ${access_token}`
}
});
const user = await userInfo.json();
// {
// "email": "user@example.com",
// "email_verified": true,
// "name": "John Doe",
// ...
// }
```
#### Token Refresh
When the access token expires (after 2 hours), use the refresh token to get a new one:
```javascript theme={null}
const response = await fetch("https://clerk.coloop.ai/oauth/token", {
method: "POST",
headers: {
"Content-Type": "application/x-www-form-urlencoded",
},
body: new URLSearchParams({
grant_type: "refresh_token",
client_id: "your_client_id",
refresh_token: "your_refresh_token",
// Include client_secret only for private applications
...(isPrivateApp && { client_secret: "your_client_secret" })
})
});
const tokens = await response.json();
```
#### Security Considerations
1. **Token Storage**
* Store access tokens and refresh tokens securely
* For public applications, use secure browser storage mechanisms
* For private applications, use server-side secure storage
2. **PKCE Verifier**
* Generate a new code verifier for each authorization request
* Store the verifier securely until the token exchange
3. **Error Handling**
* Handle token expiration and refresh scenarios gracefully
* Implement retry logic with exponential backoff for failed requests
# OAuth Application Setup
Source: https://docs.coloop.ai/docs/api/authentication/setup
To integrate with CoLoop, you'll need to provide us with the following information:
1. **Application Name**: A name to identify your integration (e.g., "Your Product Name")
2. **Callback URL**: The URL where users will be redirected after authenticating with CoLoop (e.g., `https://yourdomain.com/oauth2/callback`)
3. **Application Type**: Whether your application is public or private
* Choose **private** for server-side applications that can securely store credentials
* Choose **public** for client-side applications (browsers, mobile apps) that require PKCE flow
Once you provide this information, we'll create an OAuth application for you and provide you with the necessary credentials and endpoints.
### Response Format
For private applications, you'll receive the following configuration:
```json theme={null}
{
"object": "oauth_application",
"id": "oa_xxx",
"instance_id": "ins_xxx",
"name": "Your App Name",
"client_id": "your_client_id",
"client_secret": "your_client_secret",
"public": false,
"scopes": "email profile",
"callback_url": "https://your-domain.com/oauth2/callback",
"authorize_url": "https://clerk.coloop.ai/oauth/authorize",
"token_fetch_url": "https://clerk.coloop.ai/oauth/token",
"user_info_url": "https://clerk.coloop.ai/oauth/userinfo",
"discovery_url": "https://clerk.coloop.ai/.well-known/openid-configuration",
"created_at": 1234567890123,
"updated_at": 1234567890123
}
```
For public applications, the configuration will be similar but without the `client_secret` field and `public` set to `true`:
```json theme={null}
{
"object": "oauth_application",
"id": "oa_xxx",
"instance_id": "ins_xxx",
"name": "Your App Name",
"client_id": "your_client_id",
"public": true,
"scopes": "email profile",
"callback_url": "https://your-domain.com/oauth2/callback",
"authorize_url": "https://clerk.coloop.ai/oauth/authorize",
"token_fetch_url": "https://clerk.coloop.ai/oauth/token",
"user_info_url": "https://clerk.coloop.ai/oauth/userinfo",
"discovery_url": "https://clerk.coloop.ai/.well-known/openid-configuration",
"created_at": 1234567890123,
"updated_at": 1234567890123
}
```
### Important Security Notes
1. For private applications, store the `client_secret` securely as it cannot be retrieved later
2. Public applications use PKCE flow and don't receive a client secret
3. The provided scopes (`email profile`) allow access to basic user information
Contact the CoLoop team to set up your OAuth application during the Alpha phase. In future releases, this process will be self-serve through our developer portal.
# Getting Started
Source: https://docs.coloop.ai/docs/api/getting-started
Authenticate with the CoLoop API and make your first organization-scoped requests.
The CoLoop API enables data collection platform (DCP) developers to integrate CoLoop's AI content analysis capabilities into their applications. This guide will help you get started with the API.
## API Information
* **Base URL:** `https://api.coloop.ai`
* **Current Version:** v1
* **API Documentation:** Complete OpenAPI documentation available at [https://api.coloop.ai/docs](https://api.coloop.ai/docs)
* **API Status:** [https://status.coloop.ai](https://status.coloop.ai)
All API requests should be made to: `https://api.coloop.ai/v1/`
## Authentication
CoLoop supports API keys and OAuth 2.0. Choose the method that matches your
integration.
### API keys
Use an API key for an integration, script, or local tool tied to one CoLoop
organization. [Create and manage the key](./managing-api-keys), then send it in
the `x-api-key` header:
```bash theme={null}
x-api-key: your_api_key
```
### OAuth 2.0
Use [OAuth 2.0](./authentication/setup) when your application authenticates
individual CoLoop users. After completing the OAuth flow, send the access token
as a Bearer token:
```bash theme={null}
Authorization: Bearer your_access_token
```
## Find your organization ID
Some API requests require the ID of the organization you want to work with. You can copy it from CoLoop:
1. Select your organization from the workspace switcher.
2. Open the organization settings, then select **API keys**.
3. Find **Organization ID**, then click **Copy**.
## Core Resources
### Projects
Projects are the main organizational unit in CoLoop. They contain resources (like transcripts and media) that you want to analyze.
#### List Projects
```bash theme={null}
GET /v1/projects/
```
Example response:
```json theme={null}
{
"projects": [
{
"id": "proj_123",
"name": "Customer Interview Analysis",
"description": "Q4 customer feedback analysis",
"createdAt": "2024-01-01T00:00:00Z",
"updatedAt": "2024-01-01T00:00:00Z",
"ownerId": "user_123",
"organizationId": "org_123",
"keywords": ["feedback", "support"],
"embeddingModel": "text_embedding_3_small"
}
]
}
```
#### Create Project
```bash theme={null}
POST /v1/projects/
Content-Type: application/json
{
"name": "New Research Project",
"description": "Analysis of user interviews",
"organization_id": "org_123"
}
```
### Resources
Resources are the actual content you want to analyze. The API supports several types of resources:
1. Transcripts
2. Media files
3. Combined transcript and media
4. Research activities with responses
#### Add Resource to Project
```bash theme={null}
POST /v1/projects/{projectId}/resources/
Content-Type: application/json
{
"external_id": "interview_123",
"name": "Customer Interview #1",
"data": {
"transcript": {
"speakers": [
{
"id": "speaker_1",
"name": "Interviewer",
"role": "moderator"
},
{
"id": "speaker_2",
"name": "Participant",
"role": "participant"
}
],
"speech_turns": [
{
"speaker_id": "speaker_1",
"content": "Can you tell me about your experience?"
}
]
}
}
}
```
## Common Patterns
### Resource Types
The API supports different types of analysis content:
1. **Interview Transcripts**
* Structured conversation data
* Speaker identification
* Timestamped speech turns
2. **Research Activities**
* Multi-respondent studies
* Task-based responses
* Mixed media support (text, audio, video, images)
3. **Media Files**
* Audio recordings
* Video content
* Images with captions
### Storage Considerations
* Projects can specify a `storageRegion` (us, uk, eu)
* Media files require a two-step process:
1. Create resource and receive upload URLs
2. Upload media to provided URLs
## Support
During the Alpha phase, contact the CoLoop team for:
* OAuth application setup
* API access questions
* Integration support
* Feature requests
## Next Steps
1. Set up your [OAuth application with CoLoop](./authentication/setup)
2. Create your first project
3. Add some resources for analysis
4. Explore the detailed API documentation at [https://api.coloop.ai/docs/](https://api.coloop.ai/docs/)
# Managing API Keys
Source: https://docs.coloop.ai/docs/api/managing-api-keys
Create, store, review, rename, and revoke API keys for your CoLoop organization.
API keys let integrations, scripts, and local tools access CoLoop without
asking a user to sign in for every request. Each key is tied to the organization
and admin who creates it.
CoLoop shows the full API key only once. Store it securely. If you need to give
it to someone else, use a purpose-built secret-sharing tool instead of email,
Microsoft Teams, Slack, or another messaging tool.
## Who can manage API keys
Only organization admins can create and manage API keys. Each admin can see and
manage only the keys they created.
If you cannot manage API keys, ask an organization admin to create or update the
key for you.
## Open the API keys page
1. Click your organization name in the top left.
2. Click **Manage**.
3. Open **API keys**.
## Create an API key
1. Click **Create API key**.
2. Enter a name that identifies where you use the key, such as
`Local data import`.
3. Click **Create**.
4. Click **Copy**, then save the key somewhere secure.
5. Click **Done**.
The new key appears in the API key list. CoLoop displays its prefix so you can
identify it without exposing the full key.
## Review your API keys
Use the API key list to check when each key was created and last used. Turn on
**Show inactive** to include expired and revoked keys.
CoLoop does not display the full key after you close the creation form. If you
lose a key, create a replacement and revoke the lost key.
## Rename an API key
1. Find the active key in the API key list.
2. Click the pencil icon in its **Actions** column.
3. Enter the new name.
4. Click the checkmark icon to save it.
Renaming a key changes only its name. The key continues to work without changes
to your integration.
## Replace an API key
Use this process when you need to rotate a key or no longer have its full value.
1. Create a new API key.
2. Update your tool or integration to use the new key.
3. Make an API request and check that the new key's **Last used** date updates.
4. Revoke the old key.
## Revoke an API key
1. Find the active key in the API key list.
2. Click the trash icon in its **Actions** column.
3. Check the key name in the confirmation dialog.
4. Click **Revoke**.
The key stops authenticating API requests and cannot be restored. Turn on
**Show inactive** to view it after revocation.
# Organisation Auto-Join
Source: https://docs.coloop.ai/docs/collab-and-access-management/auto-join-organisation
This page provides a step-by-step guide to help you set up auto-join for your organisation. By following these instructions, you'll ensure that your colleagues can seamlessly connect to your organisation as soon as they create their CoLoop account. This setup makes onboarding straightforward and helps your team start collaborating effortlessly right away.
As long as a user has admin privileges for an organisation, they can set-up organisation auto-join. This means that when other team members set up their CoLoop accounts, they will be automatically added to their organisation.
To begin with open up your organisation's home screen on CoLoop and click on your organisation's icon in the top left hand corner of the screen and select manage access, as shown below.

After selecting manage, a pop-up will appear, allowing you to manage your organisation's settings. To set up auto-join, enter your organisation's domain (e.g. @organisation.com) by selecting '+ Add domain' in the 'Verified Domains' row.

This will open a pop-up where you can choose your auto-join setting. To ensure users in your organisation are automatically added to CoLoop when their accounts are created, select the 'Automatic Invitations' option, as shown below. Please note, to be automatically added to your organisation, colleagues must set up accounts with email addresses with domains matching those listed under 'verified domains'.

# Client Access
Source: https://docs.coloop.ai/docs/collab-and-access-management/client-access
Share a password-protected, chat-only view of your project with clients. Create branded access links so clients can explore your research through chat without needing a CoLoop account.
Client access lets you share a project with clients as a password-protected, chat-only page. Clients open a link, enter a password, and chat with your project's research data — useful for letting stakeholders explore insights themselves after you've delivered the findings. They don't need a CoLoop account, and they can't see anything else in your workspace.
You can also brand the client-facing page with a header image, a public project name, a heading, a description, and suggested prompts.
Client access is rolling out gradually. If you don't see it in your project
sidebar, contact support to have it enabled for your organization.
## Set up client access
You need permission to manage project members (for example, Project Admin) to set up client access.
Open your project and select **Client access** in the project sidebar. The first time you open it, setup starts with branding the client page; after that, it opens straight to your access links. Use the numbered steps at the top to move between the two.
### Step 1: Brand the client page
The Branding step controls how the chat page looks to clients. A live preview on the right updates as you type. Every field is optional.
| Field | Details |
| :-------------------- | :-------------------------------------------------------------------------------------- |
| **Header Image** | PNG, JPEG, or WebP, up to 5 MB. Adjust the display width after uploading. |
| **Project Name** | The name clients see instead of your internal project name. |
| **Heading** | The headline on the chat page, up to 200 characters. If empty, default wording is used. |
| **Description** | A short explanation of what clients can ask about, up to 500 characters. |
| **Suggested prompts** | Up to 8 prompts shown as clickable suggestions, up to 300 characters each. |
When you're done, click **Save and continue**. Not ready to brand the page? Click **Skip and continue** — clients see a clean default page, and you can come back any time.
To go back to the default appearance later, clear the fields and click **Save and continue**.
Your internal project name is never shown to clients. If you don't set a
public **Project Name**, generic wording is used instead.
### Step 2: Create an access link
1. On the **Access links** step, click **Create Access Link**.
2. Enter a **Label** to identify the link, such as the client's name.
3. Set a **Password**. It must be 8–128 characters. Clients will need it to open the link.
4. Click **Create**.
Click **Copy Link** on the new link card and send the link and password to your client. Share the password separately from the link, for example over a different channel.
Each link card shows when it was created, when it was last accessed, and how many times it has been opened.
## Manage access links
Open the **⋮** menu on a link card to:
* **Change Password** — set a new password for the link. This signs out anyone currently using the old password.
* **Revoke Access** — invalidate the link immediately and end any active client sessions. This cannot be undone; create a new link to restore access.
You can create as many links as you need, for example one per client, so you can revoke access for one client without affecting others.
## What clients see
When a client opens the link, they see a password page with your organization's name and logo, and the public project name if you set one.
After entering the password, they land on the chat page with your header image, heading, description, and suggested prompts.
Clients can ask questions and get answers grounded in the project's research data, the same way chat works elsewhere in CoLoop, and trace insights back to the verbatim evidence behind them.
Clients cannot:
* Open raw files, transcripts, or analysis grids
* See your other projects, project members, or settings
* Navigate anywhere in your workspace beyond the chat page
A client's session lasts 24 hours; after that they re-enter the password. Password attempts are rate-limited to protect against guessing.
## Client access vs. guest access
Use client access when a client should only chat with the project's data, with no account setup. Use [guest access](/docs/collab-and-access-management/guest-access) when an external collaborator needs a CoLoop account with fuller project access, such as viewing evidence, making clips, or editing grids.
# Enforcing a Storage Region
Source: https://docs.coloop.ai/docs/collab-and-access-management/data-residency
Require all new projects in your organization to store raw data in a specific region.
Organization admins can enforce a storage region (US, UK, or EU) so that every new project in the organization stores raw files in that region. When enforcement is active, members cannot choose a different region when creating a project.
This only affects new projects. Existing projects keep the region they were created with. Storage regions cannot be changed after project creation.
## Turn on storage region enforcement
1. Click your organization name in the top left and select **Manage**.
2. Go to the **Data residency** tab.
3. Toggle **Enforce storage region** on.
4. Select the region you want to enforce: **United States**, **United Kingdom**, or **European Union**.
5. Click **Save**.
All new projects created by anyone in your organization will use the enforced region. The storage region picker in the project creation dialog is disabled, and members see a message explaining which region is enforced.
## Turn off enforcement
1. Go to the **Data residency** tab in your organization settings.
2. Toggle **Enforce storage region** off.
3. Click **Save**.
Members can then choose their own storage region when creating new projects.
## What members see
When enforcement is active, the storage region picker in the create project dialog is disabled. The enforced region is pre-selected and a message explains that the organization enforces it.
## Who can change this setting
Only organization admins can access the Data residency tab. Non-admin members see a message directing them to contact their admin.
For more on admin vs. member permissions, see [Managing an Organisation](/docs/collab-and-access-management/managing-an-org).
# Guest Access
Source: https://docs.coloop.ai/docs/collab-and-access-management/guest-access
Learn how to include external collaborators in your CoLoop qualitative projects. Follow step-by-step guidance to invite colleagues from outside your organisation, granting them tailored editing permissions to ensure smooth and efficient project collaboration.
You can now invite guests, such as clients or external collaborators, to access and contribute to specific qualitative projects.
To add guests to your project, go to your project homepage and select the three dots at the top right hand side of the project folder. Then select 'Manage access'.

After clicking on 'Manage access', you will be able to manage project members. Click on the Guests tab and then enter the email of the guest you wish to add. Then click on the drop down tab to the right to select their role.

Enter the email of the guest, and then select the level of access you would like to grant. Guests can be added as either a 'Guest Editor', 'Guest Analyst' or a 'Guest Viewer'.
| **Allowed Actions** | Guest Editor | Guest Analyst | Guest Viewer |
| ------------------------------ | ------------ | ------------- | ------------ |
| Interact with evidence panels | ✓ | ✓ | ✓ |
| Make and save clips | ✓ | ✓ | ✓ |
| Create and edit analysis grids | ✓ | ✓ | ✗ |
| Create and use chats | ✓ | ✓ | ✗ |
| Upload and edit materials | ✓ | ✗ | ✗ |
| Change permission types | ✗ | ✗ | ✗ |
After you hit 'Add', the new user will be sent an email inviting them to join the project. Once the invitation has been accepted, your new guest will appear underneath existing members.
### 
Modifying Guest Access
You can choose to modify guest access you have granted at any time. Select the the three dots on the right hand side of the guest's status to modify access. Select 'Remove' if you would like to remove full access from the project. Alternatively, select 'Change role' and update the guest's status accordingly.

Modify your guest's access by selecting which role you would like them to have and hit apply. The guest's access will now be updated.

### What can project guests see?
Project guests can only see the project they've been added to. They will not be able to see or access any other projects in your worksapce, only the projects they are members of.
When invited to join a project, guests will recieve an email prompting them to create a CoLoop account.
After logging in, guests can access the project by clicking on the guest project tab.

The guest project tab shows the project's name and description. The chat that used to run on this page has been retired. To give a stakeholder a chat-only view of a project without a CoLoop account, use [client access](/docs/collab-and-access-management/client-access) instead.
# Managing an Organisation
Source: https://docs.coloop.ai/docs/collab-and-access-management/managing-an-org
Learn how to manage your organisation, invite team members, manage roles, and optimise workspace settings for seamless project collaboration. Also learn how to set up media controls and purchase top ups.
An organisation is a shared team space that you can use to share projects for collaborative projects.
There are two ways to belong to an organisation, as an Admin or as a Member.
| **Permission / Capability** | **Admins** | **Members** |
| ---------------------------------- | ---------- | ----------- |
| Can check usage | **✓** | **✗** |
| Can manage member status | **✓** | **✗** |
| Can add and remove users | **✓** | **✗** |
| Can see all public projects | **✓** | **✓** |
| Can see all private projects | **✓** | **✗** |
| Can create projects | **✓** | **✓** |
| Can see and open all projects | **✓** | **✗** |
| Can open projects they are part of | **✓** | **✓** |
Admins have additional permissions that allow them to manage the organisation, as described in this guidance document.
## Membership Management in Your Organisation
Click on your organisation name on the top left of your CoLoop homepage and then select "Manage". Click on 'Members' to add or remove team members.
Enter in your colleagues' emails and hit invite. They will recieve an email prompting them to create their CoLoop account and join your organisation's workspace (please check spam). An invite to join CoLoop is valid for 30 days.
Admins can also change the permissions of organisation members here, but toggling between 'Admin' or 'Member' next to a user's name and email.
## Reviewing Membership Requests
As an organization admin, you may receive requests from team members who want to add people to projects who aren't yet in your workspace. You can review and manage these requests from the organization dialog.
### Accessing Membership Requests
1. Click on your organisation name on the top left of your CoLoop homepage and select "Manage"
2. In the organization dialog, click on the "Membership requests" tab
3. Here you'll see all pending requests from your team members
### Reviewing a Request
Each membership request shows:
* The email address of the person being requested
* Who requested to add them
* When the request was made
* The project they'll be added to (if applicable)
### Approving a Request
1. Click "Approve" next to the request
2. An invitation will be automatically sent to the requested person's email
3. When they accept the invitation and join your workspace, they'll automatically be added to the relevant project
4. The request will be marked as approved
### Rejecting a Request
1. Click "Reject" next to the request
2. Optionally, add a reason for rejection (this helps your team understand why)
3. The request will be marked as rejected
4. Any pending project invitations for this person will be removed
When you approve a membership request, the person will receive an email invitation to join your workspace. Once they accept and join, they'll automatically be added to the project they were originally invited to.
## Setting Media Controls for your Organisation
### Auto Media Deletion
Admins can enforce organsiation-wide deletion of media files after processing. This means, that as soon as transcripts are created for any audio or video uploaded into the platform, the audio and video files will be deleted leaving just the transcript.
We strongly recommend AGAINST setting up auto-deletion of media unless absolutely necessary. It will prevent users from being able to re-do transcriptions, use the stimulus deck concept testing method, and from cutting clips of audio and video.
### PII (Personally Identifiable Information)
Admins can enforce organisation-wide PII controls. PII is Personally Identifiable Information (such as Date of Birth, County of Origin and Name).
Admins need to click 'Manage' and then select 'Media Controls'. The relevant PII policies can be selected. These will automatically be applied to any audio or video files anyone in the organisation uploads.
## Checking Usage
Admins can also check their orgaisation's usage by clicking on the Usage Dashboard icon, found on the top left of the home page next to the organisation workspace name.
This will show admins how many transcription hours, translation hours, chat questions, analysis grid questions and projects their team has used.
## Buying Additional Hours or Open Ends Credits
Admins can also buy top ups of additional hours or questions if needed, as well as open ends credits, via the usage dashboard.
Click on 'Buy More Credits' in the top right hand corner of the usage dashboard and you'll be redirected to a checkout where you can purchase what you need.
# Managing Seats
Source: https://docs.coloop.ai/docs/collab-and-access-management/managing-seats
Learn how to view and manage seats for people in your CoLoop organisation.
A seat lets a person in your organisation use CoLoop features.
Someone can be a member of your organisation without having a seat. This is
useful when you want them in the workspace, but they do not need to work in
CoLoop yet.
Some organisations do not have seat limits. If your organisation does not have
seat limits, members can use CoLoop without being assigned a seat.
Project guests do not use organisation seats. Guests only have access to the
projects you invite them to.
## Who can manage seats?
Organisation admins and champions can manage seats for their organisation.
If you cannot see the Seats page, ask an organisation admin or champion to make
the seat change for you.
## Open the Seats page
1. Open CoLoop.
2. Click your organisation name in the top left.
3. Click "Manage".
4. Open the "Seats" page.
## Check if your organisation has seat limits
Open the Seats page.
If you see seat totals, your organisation has seat limits.
If you do not see seat totals, your organisation does not have seat limits.
Members can use CoLoop without being assigned a seat.
## Check if seats are enforced
Seat enforcement can be off while an organisation moves onto a seat-based plan.
If you see "Seat enforcement off", your organisation has seat limits, but those
limits are not controlling access yet. Members without seats can still use
CoLoop.
This gives organisation admins and champions time to review members and make
sure the right people are on the right seats before seat limits start
controlling access.
## Understand your seat summary
If your organisation has seat limits, the top of the Seats page shows how many
seats your organisation has.
Each seat type shows:
| Field | Meaning |
| --------- | ------------------------------------- |
| Used | How many seats are currently assigned |
| Total | How many seats your organisation has |
| Available | How many more seats can be assigned |
A seat type can show more used seats than the current total. This is called
over-allocated. Existing members keep their seats, but you cannot assign more
seats of that type until the number of used seats is below the total again.
If your organisation stays over-allocated, CoLoop may contact your team to help
correct the seat count.
## Seat types
If your organisation has seat limits, it has one or more seat types.
| Seat type | Best for |
| ---------- | ------------------------------------------ |
| Researcher | People who run research projects in CoLoop |
| Explorer | People who use research findings |
The seat types available to you depend on your organisation's plan.
A simple way to choose is to ask what the person comes to CoLoop to do. If they
are responsible for the research work, they should be on a Researcher seat. If
they come to CoLoop to learn from research that already exists, they should be
on an Explorer seat.
## Find members
Use the member list to find people in your organisation.
You can:
* Search by name or email.
* Filter by role.
* Filter by seat status.
* Sort by name or recent activity.
Recent activity can help you decide who still needs a seat.
## Assign a seat
Use this when someone needs to start using CoLoop.
1. Find the person in the member list.
2. Open the menu on their row.
3. Choose the seat type you want to assign.
If no seats are available for that seat type, you will not be able to assign
that seat. This includes over-allocated seat types. Contact CoLoop about adding
more seats, or remove a seat from someone who no longer needs one.
## Change a seat type
Use this when someone's needs change.
1. Find the person in the member list.
2. Open the menu on their row.
3. Choose the new seat type.
You can only change to a seat type that has an available seat.
## Remove a seat
Use this when someone no longer needs to use CoLoop.
1. Find the person in the member list.
2. Open the menu on their row.
3. Click "Revoke seat".
4. Confirm the change.
After you remove a seat, it becomes available for someone else.
## What happens if someone has no seat?
If your organisation does not have seat limits, members can use CoLoop without
seats.
If your organisation has seat limits, a member without a seat can still sign in.
They cannot use CoLoop features that need a seat. They should ask an
organisation admin or champion for a seat.
## Seats and project access are different
Seats and project access control different things.
| Setting | What it controls |
| -------------- | ---------------------------------------- |
| Seat | Whether a member can use CoLoop features |
| Project access | Which projects a person can open or edit |
For example, a person can have a seat but still need to be added to a project
before they can open it.
## Common questions
### Why can I see someone in the member list if they have no seat?
They are a member of your organisation, but they do not currently have a seat.
### Do guests use seats?
No. Project guests do not use organisation seats.
### Why can't I assign a seat?
You cannot assign a seat when no seats are available for that seat type.
If the seat type is over-allocated, no seats are available. Contact CoLoop about
adding more seats, or remove a seat from someone who no longer needs one.
### What should I do when all seats are used?
Contact CoLoop about adding more seats, or remove a seat from someone who no
longer needs one.
### Why does a seat type show more used seats than the total?
This can happen if your organisation's seat limit was reduced after seats were
already assigned. Existing members keep their seats. New seats of that type
cannot be assigned until the used number is below the total again.
# Managing Project Visibility
Source: https://docs.coloop.ai/docs/collab-and-access-management/managing-visibillity
This guidance document explains how to control who can see and access your project. You'll learn how to set initial visibility settings, adjust access for specific users, and manage permissions over time as your project evolves.
### Initial Set Up
Create your project and control who can view it by using the dropdown menu under 'Who can see this project' as shown below.
* Selecting 'All organization members' makes the project visible to everyone in your organization, meaning it will appear on everyone's CoLoop homepage.
* Selecting ' Project members only' restricts visibility to those you add to the project after creating it.

After clicking "Create," you'll be prompted to add members to your project. If you set the visibility to "Project Members Only," only the people you add at this stage will see the project on their homepage.
Please note workspace Admins can see every project regardless of its visibility.
### Managing Project Visibility
You can choose to change project visibility at anytime. To do so, click on the three dots of the project file when in your homepage and select manage access.

This will prompt a pop up. Click on the settings tab of the pop up and then change the visibility setting as needed.

# Sharing Analysis Grids & AI Chats
Source: https://docs.coloop.ai/docs/collab-and-access-management/sharing-analysis-grids-ai-chats
Learn how to share analysis grids and AI chats in CoLoop to facilitate collaboration and manage access across your organisation. Learn how to share and manage access to analysis grids, AI chats, and the benefits of pinning chats for easy access and collaboration across your team.
Researchers who are basic members or admins of the same project can collaborate on them in realtime.
## Shared Analysis Grids
By default all analysis grids are shared with the other researchers in your project. Click on one of the option on the Analysis Grid section to open one.

### Private Analysis Grids
You can make analysis grids private by clicking on the three dots next to grid name and then clicking on 'Manage Access'.

Change it from 'Shared' to 'Private'.
## Shared AI Chats
By default AI Chats are *not* shared. You can share a chat by going to the Chats section, and toggling the status of the desired chat from 'Private' to 'Shared':

The chat will then be visible to your teammates that are working in the project!
If you want to share a chat click on the three dots and change the status of the chat to ‘Shared’. You can change the status back to Private at any time.
## Pinning AI Chats
Whenever you open an AI Chat or create a new one it will be pinned to the sidebar. To unpin an AI chat click on the unpin icon next to the name of the chat in the list.

### View all AI Chats
Click on All Chats to see a list of all of the AI Chats in the project. This list is split between chats that are yours and chats that have been shared with you. Click on a chat to open the chat in your side bar.

# Sharing Projects
Source: https://docs.coloop.ai/docs/collab-and-access-management/sharing-projects
Discover how to share projects in CoLoop for real-time collaboration with your colleagues. This page explains how to share projects with other CoLoop users within your organisation’s workspace.
## Organisation Admins & Organisation Members
Researchers in an organisation can either be Members or Admins. They have different levels of privilege when it comes to accessing projects:
| Allowed Actions | Admin | Member |
| ------------------------------------------------ | ----- | ------ |
| Create Project | ✓ | ✓ |
| See a list of all projects | ✓ | ✓ |
| Open any project | ✓ | ✗ |
| Add and remove researchers from the Organisation | ✓ | ✗ |
## Project Admins and Project Basic Members
All Organisation Admins are also Project Admins and can open any project
By default the researcher who creates a project is the project Admin. This is *different* to an Organisation Admin:
| Allowed Actions | Project Admin | Project Member |
| -------------------------------------- | ------------- | -------------- |
| Add or remove members from the project | ✓ | ✗ |
| Open the project | ✓ | ✓ |
| Sharing a chat | ✓ | ✓ |
## Requesting access to a project
If you are not a Basic Member or Admin of a project or an Organisation Admin and you try to open a project you will be shown an Access Denied modal and given the option to request access.
Click on the "Request Access" button to send an email to the project Admins.
### **Project Roles**
Users can be added to projects with varying levels of permission.

| **Allowed Actions** | Admin | Editor | Analyst | Viewer |
| :------------------------------ | :---- | :----- | ------- | :----- |
| Add / Remove Users from Project | ✓ | ✗ | ✗ | ✗ |
| Change Project Visibility | ✓ | ✗ | ✗ | ✗ |
| Upload and edit materials | ✓ | ✓ | ✗ | ✗ |
| Create and edit analysis grids | ✓ | ✓ | ✓ | ✗ |
| Create and use chats | ✓ | ✓ | ✓ | ✗ |
| Interact with evidence panels | ✓ | ✓ | ✓ | ✓ |
| Make and save clips | ✓ | ✓ | ✓ | ✓ |
## Adding People Who Aren't in Your Workspace
When you try to add someone to a project who isn't already a member of your organization's workspace, CoLoop will help you invite them. What happens next depends on your role and your organization's settings:
### If You're an Organization Admin
You can directly invite anyone to join your workspace. When you enter their email address:
1. You'll see a confirmation dialog asking if you want to send them an invitation
2. Click "Send invite" to send them an email invitation to join your workspace
3. Once they accept the invitation and join your workspace, they'll automatically be added to the project with the role you selected
### If You're a Regular Member
The system determines whether you can invite someone directly or need admin approval:
**You can invite directly if:**
* The person's email domain matches a verified domain in your organization (e.g., if your organization has verified `@yourcompany.com`, you can invite anyone with that email domain)
**You need admin approval if:**
* The person's email domain is not verified for your organization
When you need admin approval:
1. Enter the person's email address and select their project role
2. Click "Send request" to submit a membership request
3. Your workspace administrators will receive an email notification
4. Once an admin approves the request, the person will receive an invitation to join your workspace
5. When they accept and join, they'll automatically be added to the project
Pending invitations are automatically resolved when someone joins your workspace. You don't need to add them to the project again.
# Transfer a Project Copy
Source: https://docs.coloop.ai/docs/collab-and-access-management/transferring-projects
Send a complete copy of a qualitative project to another CoLoop workspace.
Project transfers let another CoLoop user create a separate copy of your project in their workspace. Your source project does not change when they accept the transfer.
## Send a transfer
You need permission to manage access to the source project. The project must contain at least one file or other research resource.
1. Open the project and select **Manage access**.
2. Open the **Transfers** tab.
3. Enter the recipient's email address.
4. Click **Send transfer invitation**.
5. Copy the one-time share code that CoLoop shows after sending the invitation.
6. Send the share code to the recipient through a separate channel, such as a direct message.
7. Click **I've shared the code** after the recipient has it.
The invitation email contains a private transfer link but does not contain the share code. The share code appears only once and cannot be recovered. Send the code separately from the email.
## Accept a transfer
1. Open the transfer link in the invitation email.
2. Sign in to CoLoop.
3. Use the organization switcher to select the workspace that should receive the copy.
4. Enter the share code from the sender.
5. Click **Accept transfer**.
6. Keep the page open to follow progress, or close it and return to your project list later.
Large projects can take longer to copy because CoLoop also copies their media files. When the transfer is complete, the new project appears in the selected workspace.
## Manage a sent transfer
The **Transfer history** section shows whether each transfer is pending, copying, completed, failed, revoked, or expired.
You can revoke a pending transfer before the recipient accepts it. Invitations expire after seven days. Create a new transfer if an invitation expires, fails, or is revoked.
# What happens to my data when I upload it to CoLoop?
Source: https://docs.coloop.ai/docs/compliance/coloop-and-my-data
Discover how CoLoop ensures the security and privacy of your uploaded data for market research. Learn about data storage, processing, compliance with SOCII and GDPR standards, and user control over data retention and deletion.
This article outlines answers to the common questions users ask about how we use data uploaded to CoLoop. CoLoop is built specifically for market research agencies and ships with a range of privacy and security features built in. These are designed to make it easy for researchers to secure, manage, minimise and delete data as and when they need to.
## Raw File Storage
* When users create a project in CoLoop they asked to pick a region to securely store raw uploaded files
* This region can be EEA; UK or US.
* Any uploaded raw data e.g. Audio, Video, Excel, Transcripts etc. are then stored on encrypted AWS servers within that region.
## Processing and storage of data
### Data Onboarding
* Audio and video files are sent to a fully SOCII and GDPR compliant US transcription provider
* Files are held temporarily (typically for a few minutes) while they are transcribed
* The resulting textual information, now of a lower classification is retained securely on AWS / GCP servers operated by CoLoop in the US.
* High classification raw data is completely wiped and the only remaining copy stored on AWS servers in the selected country of origin by CoLoop.
* No data of any kind is retained by the transcription provider after this processing step.
### During Analysis
* Once processed and stored, further features are extracted from textual data and stored in order to be queried
Features are extracted using a range of 3rd party APIs listed [here](https://genei.notion.site/Compliance-and-Information-Security-577cdf371a6b4696932e91ebe8440d0b).
* During the analysis stage when users query the data derived features are processed securely by 3rd party APIs.
* All 3rd parties we work with are vetted and where appropriate bound by strict DPAs to prevent retention of or training on any data sent to them.
### CoLoop Data Retention
* Users of the CoLoop platform remain in control of the uploaded data at all times.
* Specific resources or entire projects can be deleted immediately and permanently in a single click through the platform or within 30 days of an email to [support](/docs/troubleshooting/contact-support).
* Data is not automatically removed by CoLoop after a certain period and will remain securely stored unless otherwise instructed by the platform user in the manner outlined above.
# Security & Ethics - how does CoLoop remain secure
Source: https://docs.coloop.ai/docs/compliance/security-and-ethics
Discover how CoLoop maintains robust security measures and ethical standards to protect user data. Learn about third-party vendor management, data localization compliance, and approaches to mitigate AI biases in research tools.
At CoLoop, we are committed to maintaining the highest standard of privacy, security and compliance. In this document, we outline the key points and describe the measures CoLoop puts in place to ensure your data privacy, ownership and ultimate control are respected.
## Third-party Vendors
3rd party vendors are a particular consideration when evaluating AI tools. This is because a vast majority of AI application providers rely in some way or another on privately hosted "Foundational Models".
### Foundational models, GPT and OpenAI
* Foundational Models are large multimillion parameter AI models that are trained on a vast corpus of data.
* They are often the starting point for adaptation for downstream tasks e.g. transcription, summarisation, search etc.
* The most famous of these at the time of writing are the GPT-n\* series of models from OpenAI
**So why does this matter..?**
* The source code and “weights” (specific configuration obtained through training) for the GPT-n series are privately held and closely guarded IP\*
* At the time of writing no other AI company currently possesses models with equivalent performance to the GPT-n models across almost all categories (this may be about to change with [Llama-2](https://ai.meta.com/llama/))
* In short, for most, access to the best in class technology only comes from privately operated foundational models whose precise configuration is deliberately obscured
\**GPT-2 is publicly available*
### What to look out for in new AI tools?
* When looking at any new AI tool it is important to review which 3rd party vendors they are working with.
* You should check that they have adequate provisions in place to guarantee that those 3rd parties are subject to the same or higher restrictions as the company providing the tool.
* This could be...
* Adherence to industry standards (ISO / SOC)
* Written guarantees
* Data processing agreements ([read more about this](/docs/compliance/security-and-ethics#data-localization))
* These agreements should align with the developer guarantees about the tool i.e. If they say they aren't using your data for training 3rd party agreements should state that as well!
### What do we do at CoLoop?
1. **Equivalent Provisions:** All 3rd party providers we work with our bound by equivalent provisions to those in our own [Data Processing Addendum (DPA)](https://trust.coloop.ai/resources?s=mpofiuubxodw5x3gp8lcoj\&name=data-processing-addendum-dpa) and [Privacy Policy](https://www.coloop.ai/privacy-policy). This includes OpenAI who are contractually restricted from using any data they come into contact with for the improvement of their product and services.
2. **Data Minimization**: All systems are engineered to provide limited access to data strictly defined by their function. Data is only shared with each service where required.
3. **Vendor Management:** All 3rd parties are vetted to ensure compliance with our standards when being considered, and their register is maintained in our [AI Overview Document](https://trust.coloop.ai/resources?s=e6rmtia69tsokejqjuja58\&name=co-loop%E2%80%99s-underlying-ai-models.pdf).
## Data Usage
[Foundational Models](/docs/compliance/security-and-ethics#foundational-models-gpt-and-openai) are adapted or improved for specific tasks through training. A base model such as GPT4 could be improved to answer questions about life sciences by fine-tuning it on many 1000s of pieces of text from say academic papers about life science. The resulting model would end up better on text based tasks to do with life sciences.
### How does this impact privacy?
* Language models are primarily trained using [Next Token Prediction](https://twitter.com/cwolferesearch/status/1669811217148289026) which basically means predicting which sub-word comes next in a sentence e.g. “The cat sat on the …”
* If the underlying data it was trained on contained many references to a piece of personally identifiable information e.g. Somebody’s name “John Doe”;
* When prompted with “John” it would become more likely to predict “Doe” as the next word.
* This could have disastrous consequences as the underlying models would then be liable to ‘leak’ pieces of its training data such as “John Doe” and whatever else he was mentioned in conjunction with if prompted correctly.
### How do I know whether a service is learning from my data?
* You need to check the privacy policy and any other associated service agreements or data processing agreements for something to the effect of "your data may be used for the improvement of our products and services"
* It is important to note that simply passing data into an AI model after it's been trained to get a result (termed 'Inference') does not cause it to learn from your data
### What to look out for?
* Make sure the tools you are looking at are clear about whether your data will be used for *training*
* It is important to be specific on this point!
* Many products gather anonymised analytics for reasonable purposes such as KPI tracking e.g. How many people logged in this week.
* Often these in product analytics are too noisy or few to have any trainable value
* Companies are extremely unlikely to be actively dishonest on this point
* The penalties for misuse of customer data in this fashion are extremely severe and increasingly under review
* Do also remember that these policies can be updated from time to time - you should be notified in writing when this occurs!
### What do we do at CoLoop?
* At CoLoop we **NEVER** use your data for any kind of training.
* Data is used exclusively in the manner outlined in our [Data Processing Addendum (DPA)](https://genei.notion.site/CoLoop-Beta-c0b92434375040b084348b4485ad7d23#:~:text=%F0%9F%94%92%C2%A0Compliance%20and%20Information%20Security) and [Privacy Policy](https://genei.notion.site/Privacy-policy-c1fe81d698794f6ab559812dea45b84d)
## Transparency
AI models are in many ways still a black box. Just like the human brain, researchers are aware of their properties and behaviour. They know broadly which neurons are lit up by certain stimuli and how they adapt under training. They know what happens when broad groups of neurons are disabled in some way and how that can affect the performance of the overall system on a set of baseline tasks. They don’t typically have a deep and fundamental understanding of what goes on inside that enables the outputs to be derived from the inputs. Also just like the human brain this doesn’t stop somebody from **interpreting** the output of a system perfectly well.
When evaluating a system it is important to make a distinction between **explainability** and **interpretability** which according to [*"Explainable AI: A Review of Machine Learning Interpretability Methods"*](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7824368/#:~:text=One%20of%20the,rigorousness%20%5B17%5D.) is defined as:
**1. Interpretability**: Is the “the ability to explain or to present in understandable terms to a human ... The more interpretable a machine learning system is, the easier it is to identify cause-and-effect relationships within the system’s inputs and outputs”.
**2. Explainability**: Is the depth to which the internal procedures that are taking place during training and inference are understood.
### When is this a problem?
* AI systems can ‘make decisions’ which impact the lives of real people for instance: deciding whether somebody is approved for a mortgage; deciding whether a patient is eligible for a certain treatment or deciding whether an autonomous car should protect the pedestrian or the driver…
* Most individuals and legal frameworks are increasingly and rightly expecting that these systems should be able to explain their decision making to affected parties. [*(“Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges”)*](https://link.springer.com/chapter/10.1007/978-3-030-32236-6_51)
* To truly realise the potential of AI there are many situations where it would be necessary to defer entire decisions to a ~~machine we cannot~~machine. We cannot however live in a world where the rationalisation for ~~live~~life changing decisions becomes “because the computer said no…”
### When is this not a problem?
* The popular model right now for AI tooling is the 'copilot' or assistant that preserves the agency of the professional while supporting them in decision making
* While the inner workings of these systems may not be strictly **explainable** they remain reasonably **interpretable**
* This means it is possible for a user to rationalise about where an output came from given the input by showing both of these side by side for instance.
* This is a popular approach with large language models that I would refer to as 'post-hoc' interpretability [*("Explainable AI: A Review of Machine Learning Interpretability Methods
")*](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7824368/#:~:text=Upon%20identifying%20the,methods%20is%20ideal.)
### What should I look for in AI tools to make sure this is addressed?
* When looking at an AI tool it is important to make sure you can at the very least rationalise in a post-hoc manner where the output comes from.
* Is it really collaborating with you as a junior researcher or are you required to treat the outputs of a less qualified colleague as gospel without question?
### What do we do at CoLoop?
* At CoLoop we link every single generated output right back to the original source material
* You can even click through and see the quote in-situ in the transcript and replay the original audio if you want to
* We also provide up and down votes with every generation to allow users to flag when the result does not align with their interpretation
* These votes are tracked internally as a KPI and used as a benchmark against which we compare future updates
## AI Ethics (Bias / Accuracy)
* The debate around AI ethics in research other than the points discussed above focus largely on bias.
* Bias in AI models is defined as systematic misrepresentations, attribution errors, or factual distortions that favor certain groups or ideas, perpetuate stereotypes, or make incorrect assumptions based on learned patterns. [*("Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models
")*](https://arxiv.org/abs/2304.03738)
* Language models are prone to absorb biases present in the textual data they are trained on.
* These biases can often manifest as [“Hallucinations”](https://en.wikipedia.org/wiki/Hallucination_\(artificial_intelligence\)) (also called “confabulations” or “delusions”) that consist of confident sounding generations that contain factual inaccuracies.
1. Demographic bias: over / under representation of certain groups
2. Cultural bias: perpetuation of stereotypes
3. Linguistic bias: overrepresentation of dominant languages e.g. English over ‘low resource’ languages e.g. Swahili
4. Temporal bias: lack of up to date information
5. Confirmation bias: reinforcement of pre-existing stereotypes
6. Ideological / Political bias: preference for a particular political view or ideology
* At present significant effort is expended by large AI model providers such as OpenAI to address this through [“AI alignment”](https://openai.com/blog/our-approach-to-alignment-research)
* It’s also worth noting that AI models suffer to much lesser extent from cognitive biases that affect human researchers such as In-group bias; relativity bias [and others](https://en.wikipedia.org/wiki/List_of_cognitive_biases)
### How are these effects mitigated in AI research tools?
* There are many approaches that can be taken to mitigate the effects of bias in AI models, some of these include
1. Fine tuning / alignment: Special training regimes undertaken by language model providers to eliminate biases or other harmful outputs (try asking ChatGPT which political party it voted for..!)
2. Curated datasets: Review and curation of datasets before training to ensure they are balanced
3. Post-hoc emergent analysis: analysis of the output of models against a test set of inputs (e.g. prompts for language models) to test them for biases to eliminate with fine-tuning or removed with a second pass to correct the generated output
4. Grounded Generation: Providing the model with additional instructions, context or information to base its generation on
5. Traceable / Interpretable outputs: Building models into AI tools in a way that enables researchers to reason about where the generation came from to ensure [transparency](/docs/compliance/security-and-ethics#transparency)
### What to look out for in AI tools?
* Does the tool use AI models that have been aligned / evaluated for bias e.g. Claude, GPT-n etc.
* Are these models deployed in a manner that puts researchers in the loop to check outputs for existing or residual bias even after alignment?
* Are outputs traceable or interpretable so the systems 'reasoning' can interpreted and checked
### How do we address this at CoLoop?
* At CoLoop we deploy all of the outlined steps above to limit the effects of this on our outputs
* All generations are fully interpretable and can be traced back to their sources
* We are additionally working to implement more post-hoc analysis on top of what we already offer to further limit the prevalence of these types of bias
## Data Privacy & Security
### How is the confidentiality of data ensured at CoLoop?
At CoLoop data privacy and security is immensely important to us and we are currently deployed with clients in sensitive areas such as government and healthcare. Although the full list of implemented controls is available on our [trust center](https://trust.coloop.ai/controls), some of the most important measures we take to guarantee this include the following:
* All data is encrypted securely at rest and in transit using AES-256 and TLS or equivalent
* We are fully compliant with SOC 2, with the certificate available on our [trust center](https://trust.coloop.ai/resources?s=mqlhp0myoroztnmnuydqkf\&name=soc-2-type-2-report)
* Systems are built and configured in line with the industry standards such [NIST](https://www.nist.gov/) regulations
* Data is stored and processed on machines housed in secure data centres hosted by AWS
* Data belonging to different customers is logically segregated on our systems
* We have legally binding agreements in place to protect client information, including Privacy Policy, Data Processing Agreements and NDAs
* We make it possible for clients to remove unnecessary PII data points before processing to ensure data minimisation
## Data Localization\*
Data localization with any saas tool has become an important topic in recent times. Different jurisdictions have different rules for what can be done with data derived from citizens living under their laws. The main concern around this point for regulators is not so much where the data actually resides but rather what laws it is subject to. Currently, CoLoop is fully GDPR compliant, but we are happy to discuss any other legal and regulatory requirements that you might have.
### Is it GDPR compliant if the data is hosted in the US?
* If the service you are interacting with is owned / operated by a UK / EEA based software company, even if the data is hosted on servers physically outside this region, the data processing can be GDPR-compliant. The company is responsible to ensure the data is processed, collected and stored securely and in line with all the GDPR requirements.
### **What if the software company is using a non-EU based 3rd party like OpenAI?**
* If the service you are interacting with uses 3rd parties that are non-EU owned or operated, then they should establish a [data processing agreement](https://trust.coloop.ai/) that contains [standard contractual clauses (SCCs)](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/international-transfers/) with those 3rd parties. Additionally, apart from the SCCs, they could rely on other transfer mechanisms, such as the [US Data Privacy Framework](https://www.dataprivacyframework.gov/s/program-overview), or Adequacy Decisions. The company should be able to produce a list of all the subprocessors that handle your data, and the transfer mechanisms in place.
### How do we address this at CoLoop?
* Data is processed by CoLoop outside of the EEA / UK in GDPR compliant manner
* Data minimisation features are enabled within CoLoop to enable users to store high classification Personal Data in the region of origin. We also perform Data Processing Impact Assessments (DPIA) and Data Transfer Impact Assessments (DTIA) wherever necessary.
* All data is encrypted at rest and in transit using AES-256 and TLS respectively, and all the third parties used by CoLoop have entered into binding DPAs with adequate transfer mechanisms in place. You can find a list of all of CoLoop’s subprocessors [here](https://trust.coloop.ai/subprocessors).
## Data Retention
Providers of AI tools may wish to retain data for training; evaluation and in some cases prevention of abuse. Information on this can usually be found in the privacy policy published by the providers of the AI tool. You should make sure you are clear on the retention policy and how to go about removing your data. It is worth noting that good engineering practices will also involve storing back ups which may also need to be removed.
### What do we do at CoLoop?
At CoLoop data is only processed or retained on your instruction. Personal Information and Client Data is deleted within at most 30 days of a request to CoLoop either written or submitted via the platform. Similarly, our subprocessors retain the data only for as long as it is needed for the agreed processing to take place.
# Analyzing Concepts
Source: https://docs.coloop.ai/docs/concept-testing/analysing-concepts
This document will show you how to analyze concepts in the grids and the chats.
### Filtering Concepts in the Analysis Grid and AI Chat
Once you've set up concept testing in your project, you will be able to filter and analyze by concepts in the analysis grid and AI chat. Concept analysis will specifically find text segments labelled by concepts to help shortlist relevant evidence.
### Analysis Grid
To use concept testing mode in the analysis grid press the '#' key when creating a question and select the concept you want to filter for. Participants who do not have text associated with a concept will not generate an answer. Concept analysis in the grids can return descriptive information on strengths and weaknesses of a specific concept.

Using the grids is a great way to analyze your concepts in CoLoop. Ask simple, specific questions about your concepts. For example:
* 'What did participants think about #Concept A?'
* 'What did people like about #Concept B?'
* 'What were the weaknesses of #Concept T'?
Start broad and then narrow do. Look at the main themes CoLoop shows you in the overview sections and then go narrower by asking more specific questions about those themes.

### AI Chat
With Chat 2.0's concept analysis capabilities, you can simply query for a concept analysis and the chat will assign positive, negative, neutral, or unknown sentiments to each of your participants. Running concept analysis in the chat will allow you to see exactly how participants perceive a concept with a quantitative count at the top and qualitative evidence below separated into sentiment buckets.
Try prompts like:
* 'Run concept analysis on Concept Y'.

# Stimulus Deck Concept Testing
Source: https://docs.coloop.ai/docs/concept-testing/stimulus-deck-concept-testing
CoLoop detects your slides in interview recordings automatically, tagging concepts as they appear on screen. This guide walks you through setting up and using a stimulus deck in your project workflow.
Navigating this page:
* [**Stimulus Deck Concept Testing**](/docs/concept-testing/stimulus-deck-concept-testing#when-to-use-a-stimulus-deck)
* [**Multiple Concepts per Slide**](/docs/concept-testing/stimulus-deck-concept-testing#multiple-concepts-per-slide)
* [**Multiple Decks in One Project**](/docs/concept-testing/stimulus-deck-concept-testing#multi-market-%26-multi-deck-projects)
### When to use a stimulus deck
CoLoop identifies and tags concepts automatically during video analysis by matching what appears on screen in your recordings against the stimulus deck you upload.
This method requires 2 components for accurate results.
* You'll need to prepare a stimulus deck with the parameters below.
* You'll need to show this exact deck during interviews and have it presented full-screen in the recordings.
Color tagging is no longer required. CoLoop used to ask you to add colored label boxes to each slide and pick that color in the app. Slide detection is now automatic, so your deck needs no tags, labels or other preparation. Projects already set up with color tagging keep working.
# Concept Testing using a Stimulus Deck
### Prepare your stimulus deck
To ensure effective concept tagging, follow these steps when creating your stimulus deck:
**One Concept Per Slide**: Each slide should focus on a single concept, whether it’s an image or text.
*If you have more than once concept per slide* [*please see below*](/docs/concept-testing/stimulus-deck-concept-testing#multiple-concepts-per-slide)
**Export as PDF**: Export the deck exactly as you showed it. Do not re-order or restyle the slides, as CoLoop matches your recordings against these exact slides.
Be sure to present this deck during your interviews and confirm that the recording clearly captures the slides.
### Set up your project
Once your stimulus deck is ready and you've collected your data, you can set up your project in Coloop:
1. **Create a New Project**:
* Log into Coloop and create a new project as you normally would.
* Upload your discussion guide if applicable.
2. **Enable Concept Testing**:
* Turn on the “concept testing” feature within your project settings.

* Input all relevant concept names into Coloop so they can be linked to their respective slides later.
### **Upload your slide deck**
* Upload your prepared slide deck into CoLoop.
* Please note your slide deck must be in PDF format.

3. **Import Video Content**
Import the video files of your interviews using the 'Video' import function.
4. **Verify Auto-Labeling**
Before proceeding and transcribing video content:
1. Review auto-labeled PDFs generated by Coloop after uploading your files.
2. Ensure that all concepts have been matched to the right slides. Click 'Complete' to review the pdf.
5. **Transcribe Videos & Assign Concept Decks**
Transcribe your videos following these steps:
1. Set language preferences and specify the number of speakers involved in discussions.
2. Select the uploaded slide deck as a reference point during transcription setup.
3. After transcription is complete, confirm speaker identities within Coloop’s interface.
6. **Review Transcripts and Check Concept Tags**
* Review auto-tagged text segments that correspond to specific concepts visible on-screen at particular times during discussions.
* This allows you to analyze participant feedback directly tied to individual concepts without manual effort.
* If a file finishes with no concepts tagged, the Files list shows a **No concepts detected** warning. See [When No Concepts Are Detected](/docs/concept-testing/tagging-concepts-no-slide-deck#when-no-concepts-are-detected) for how to retry or dismiss it.
# Multiple Concepts Per Slide
We strongly recommend having one concept per slide wherever possible.
CoLoop detects which slide is on screen, not which part of a slide a participant is discussing. Therefore, if any slides contain more than one concept you will need to follow these steps:
1. Label such slides under one title (e.g., “multi”) within your stimulus deck before uploading it into Coloop.

2. Add additional labels manually to the PDF once loaded into CoLoop in the files section. Open the PDF and edit concept labels. Press submit when ready to confirm labels.

CoLoop will automatically apply all the labels you assign to the slide to any relevant sections while that slide is onscreen. You can review and edit these labels afterward if needed.
# Multi-Market & Multi Deck Projects
Stimulus decks are especially helpful when you're running multi-market or multi-language concept tests and have separate decks for each group.
It’s ideal when:
* You have multiple decks (e.g. English, French) with the same concepts presented in each slide
* Each slide shows one concept, in the same order across all versions
* Participant videos are recorded while they view the matching deck
This setup allows CoLoop to accurately identify concepts across different markets, even if the deck content is translated, by matching the slide layouts it sees on screen.
### Prepare your stimulus decks
To prepare, keep the same concepts in the same slide order across all of your decks.
Like in the example below, the English (left) and French (right) decks have slightly different content on them but the concepts and slide order are exactly the same.

### Set up your project
Set up your project in the same way outlined above. Where translated decks share the same layout and slide order, you only have to upload one version of the stimulus deck.
In the example below, only the English version of the deck was uploaded, but the concepts were detected correctly in both the English and the French recording.


# Concept Testing with No Stimulus Deck
Source: https://docs.coloop.ai/docs/concept-testing/tagging-concepts-no-slide-deck
This document will explain how to do concept testing in CoLoop without a stimulus deck.
Use this method when you discuss concepts, products, brands or messages in-person. This flow also works when you are uploading audio or have video recordings don't show a stimulus deck.
To turn on concept testing, enter a list of concepts, brand names or any other key phrase during the project setup. CoLoop will automatically label text segments when concepts are explicitly mentioned in the transcript.
* These will appear in the transcripts and evidence panel
* Concepts entered here will be passed into the Key Phrases section when transcribing any audio or video files
### Before Setting Up
Here's some tips to take into consideration before recording and help ensure your concept testing project is analysed smoothly.
**Choose distinct concept names**
* Use concept names that will stand out:
* Good: Alpha, Beta, Gamma, A1, B2, T4
* Bad: Concept I, 1, A
* Generic sounding terms are difficult to discern and may not be picked up in the transcript.
**Reference the concepts clearly in your interviews**
* Be consistent with terminology when referring to concepts.
* Introduce concepts clearly in the interview and make sure these come through in the transcript.
### Setting Up
**1. Enable Concept Testing**
* Enable concept testing and enter your concept names.
* Add synonyms where relevant:
* You can add synonyms for each concept so the system recognises alternative ways participants might refer to it. This helps ensure all mentions are captured during analysis.
**Examples:**
* **BenchSci** → Add synonym **"BS"** if participants might use this abbreviation.
* **Benchling** → If you’re showing a distinct product stimulus (e.g., the pink version), add **"Pink"** as a synonym so colour-based mentions are linked back to the concept.
> **Tip:** Synonyms can be abbreviations, nicknames, or descriptive terms.
* For multi-market studies, include foreign language versions of concepts as synonyms (e.g., how they are spoken or written in other languages).
**2. Upload Data Files**:
* Upload audio, video, or text transcripts related to your study.
* If using audio or video files, transcribe them within CoLoop and confirm speaker identities.
**3. Check Concept Tagging**
* Once files are uploaded, review whether concepts have been tagged correctly.
* Without a stimulus deck, CoLoop only tags text segments that directly mention the entered concept names or their synonyms.

### When No Concepts Are Detected
If concept detection finishes without tagging anything in a file, the Files list shows a **No concepts detected** warning on that file with two actions:
* **Retry** runs concept detection on the file again. Use this after fixing the likely cause — for example, adding synonyms for the ways participants referred to a concept, or correcting the transcript.
* **Dismiss** clears the warning from the file. Use this when the file genuinely doesn't mention any concepts, such as a warm-up session or a group that wasn't shown the stimulus.
Dismissing applies to everyone in the project. If concept detection runs on the file again and still finds nothing, the warning reappears.
To clear the warning on several files at once, select them in the Files list and run **Dismiss no concepts detected warning** from the batch actions.
### Bulk Concept Tagging
Since this method will only tag explicit mentions of the concept in the transcript, you can bulk apply concepts where required. Highlight the desired segments of text, click '+ Add concept.' Then select the concept and click confirm.

### Analysing Concepts
To understand how you can leverage concept labels in both the grids and chats, please find more information [here](/docs/concept-testing/analysing-concepts).
# Community Data
Source: https://docs.coloop.ai/docs/file-formats/community-data
Upload and browse qualitative data from market research online communities.
CoLoop supports community data from market research online communities, including discussion forums, diary studies, and interactive tasks.
## Upload community data
1. Export your data by following the guidance for your community platform below.
2. Keep the exported files unchanged so CoLoop can process their original structure.
3. Upload the files to your CoLoop project.
Editing an exported file before uploading it can prevent CoLoop from processing it. Contact [support@coloop.ai](mailto:support@coloop.ai) if your upload fails.
If your platform is not listed, compare your export with the [Excel formatting guidelines](/docs/file-formats/excel) and contact support before uploading it.
## Browse responses
1. Open the processed community data file in your project.
2. Select **By activity** to choose an activity and task, then review every participant response to that task.
3. Select **By participant** to choose a participant, then review all of their responses grouped by activity and task.
4. Select a participant name in the activity view to open that participant's responses directly.
Images, audio, and video appear with the response they belong to. You can retry the media request if an item fails to load.
# DOCX & TXT Transcripts
Source: https://docs.coloop.ai/docs/file-formats/docx
Here, you'll learn best practice and formatting tips for how to upload transcripts seamlessly and quickly.
CoLoop can process transcripts in both .docx and .txt format. **Most transcript formats will work automatically** - CoLoop uses AI to intelligently identify the structure and speaker patterns in your transcripts.
## What CoLoop needs
For CoLoop to accurately process your transcript:
* All text in a transcript **must** be attributable to a speaker
* All speakers must be labelled (CoLoop will assign Moderator and Participant roles)
* Keep one interview per file
## How CoLoop processes transcripts
CoLoop uses AI to automatically detect and parse various transcript formats. You don't need to worry about specific formatting - just upload your transcript and CoLoop will figure out the structure.
### **Examples of transcripts CoLoop can read**
**Standard format with speaker labels:**
```
Moderator:
Hi! There welcome to the interview.
Participant 1:
Hello -- thanks for having me!
```
```
Moderator: Hi! There welcome to the interview.
Participant 1: Hello -- thanks for having me!
```
*Downloadable Example* [Here](https://coloop-public.s3.eu-west-2.amazonaws.com/qual/Focus_Group_Transcript_Example.docx)
*Downloadable Example Anonymised Names* [Here](https://coloop-public.s3.eu-west-2.amazonaws.com/qual/Focus_Group_Anonymous_Transcript_Example.docx)
**Single letter format (M/R):**
```
M: Hi! There welcome to the interview.
R: Hello -- thanks for having me!
```
*Downloadable Example* [Here](https://coloop-public.s3.eu-west-2.amazonaws.com/qual/M_R_Interview_Example.docx)
**Format with timestamps:**
```
Moderator (00:00:11 - 00:00:30)
Hi! There welcome to the interview.
Amelia (00:00:31 - 00:00:55)
Hello -- thanks for having me!
```
**Bold/normal formatting:**
CoLoop can process transcripts where moderator text is in **bold** and participant responses are in normal text, without requiring explicit speaker labels.
**And many more formats** - including transcripts from Forsta, Rev.com, Sago, SyncScript, Tellet, and other providers.
## Before uploading
Make sure:
1. There is one interview per file
2. Speaker labels are unique (if you're adding segment data via spreadsheet, make sure names match exactly)
## Using 3rd party transcripts from focus groups
If you have access to the original audio and it is in a language we support and under 10 speakers total you can also upload, transcribe and translate this directly in CoLoop
In some cases 3rd party transcripts of focus groups may not contain speaker level identification, only moderator and participants.
* Here we recommend merging together participants into a generic speaker label
* You can do this by running a find & replace on all instances of respondent
* And replacing them with something generic like "Focus Group 2 Participants"
* This approach will come with the drawback that theme counts will no longer be accurate
* It will also only be possible to summarise responses from the concensus of the whole group
## Troubleshooting
### If CoLoop can't process your transcript
In rare cases where CoLoop's AI can't automatically detect your transcript structure, you can manually override the formatting:
You must make sure the labels **exactly** match the ones shown below.
Follow these steps:
1. Prepend all moderator names with `CoLoop::R`
2. Prepend all participant names with `CoLoop::P`
3. Speaker labels must be on a new line preceding the text segment they apply to
**Example**
Below is an example of the original transcript and the edited transcript. When doing this you must make sure:
1. The text matches up *exactly* - it is case sensitive so you must prepend speakers with `CoLoop::R` or `CoLoop::P` accordingly
2. When doing your find and replace, look for a text string that does not appear in the middle of a text segment. Typically the easiest way to do this is to ensure you are finding examples of names which come after a newline
3. Newline characters can be captured in MS Word by using the `^p` wildcard (more details [here](https://answers.microsoft.com/en-us/msoffice/forum/all/how-to-find-and-replace-line-breaks-in-microsoft/e662d18c-8c22-424f-91f3-521d543e8af2))
**Original Transcript**
```txt theme={null}
Moderator
All right, well, let's go ahead and get started. So, my first question, amelia, I'll start with you on this one. Each of you is here because you said that this election, you voted for the very first time. And so I want to hear from each of you. Why did you decide to vote? Why participate in this election? So, Amelia, we'll start with you first.
Amelia
St sure. So, the last election, I was 19, so I was able to vote, but I didn't feel that I was educated enough on who to vote for to make a correct decision, and I didn't want to follow through with that. Now, this election, I'm a little bit older, and I think I have formed enough of an opinion to feel confident in my vote.
Moderator
Great. How about Dylan C. You say you voted for the first time in this election. Tell me a little bit about why you decided to participate this time.
Dylan C.
Yeah, so last election, I was 17, so I was not able to vote, and now I'm 21, so basically it was my first time being able to, and, yeah, kind of like the same thing Amelia said. I just felt like I was able to form enough of my own opinion to be able to voice it.
```
**Edited Transcript**
```txt theme={null}
CoLoop::R Moderator
All right, well, let's go ahead and get started. So, my first question, amelia, I'll start with you on this one. Each of you is here because you said that this election, you voted for the very first time. And so I want to hear from each of you. Why did you decide to vote? Why participate in this election? So, Amelia, we'll start with you first.
CoLoop::P Amelia
St sure. So, the last election, I was 19, so I was able to vote, but I didn't feel that I was educated enough on who to vote for to make a correct decision, and I didn't want to follow through with that. Now, this election, I'm a little bit older, and I think I have formed enough of an opinion to feel confident in my vote.
CoLoop::R Moderator
Great. How about Dylan C. You say you voted for the first time in this election. Tell me a little bit about why you decided to participate this time.
CoLoop::P Dylan C.
Yeah, so last election, I was 17, so I was not able to vote, and now I'm 21, so basically it was my first time being able to, and, yeah, kind of like the same thing Amelia said. I just felt like I was able to form enough of my own opinion to be able to voice it.
```
### Using Find and Replace
You can open DOCX transcripts in Word and use the find and replace feature to edit them quickly (details [here](https://support.microsoft.com/en-gb/office/video-find-and-replace-text-6f0f7d58-9b49-4a14-aba8-1de2195c0ab6))
# Spreadsheets
Source: https://docs.coloop.ai/docs/file-formats/excel
How to import spreadsheet files into CoLoop, map columns to participants, responses, and segments, and configure workbooks for analysis.
CoLoop supports the analysis of data from spreadsheet files. This can be useful for analyzing:
* MROCs
* Online Qual Projects
* Open Ended Responses
* Interview Notes
CoLoop accepts two spreadsheet formats:
* **.xlsx** (Excel workbooks), which can contain multiple sheets
* **.csv** (comma-separated values), which are imported as a single sheet
Both formats go through the same column mapping and import flow.
## Format your spreadsheet files
Check the list of [supported community data formats](/docs/file-formats/community-data) before editing your data. CoLoop supports several providers out of the box.
CoLoop reads the first row of each sheet as column headers. You may need to edit your files so the first row contains your question or title headers, with participant responses starting immediately on the second row.
Spreadsheet file uploads are capped at 500 rows per file. Break larger datasets into smaller files before uploading.
## Upload your spreadsheet file
Click **Process community data** to open the import mapping preview.
## Map columns
When you open the import preview, CoLoop shows a data grid with a sample of your rows and one tab per sheet in your workbook. CSV files appear as a single sheet. CoLoop auto-detects likely column types based on header names, so many columns will already be mapped.
CoLoop only supports free text responses. Multimedia participant responses (audio, video, and image) are only available for [Recollective](/integration/integration/recollective) and [Incling](/integration/integration/incling) projects.
### Toggle columns on and off
Each column header has a toggle switch. Turn it on to include the column in your import, or off to ignore it.
### Set column types
When a column is toggled on, use the dropdown next to the toggle to set its type:
* **Participant** — the column that identifies who said what (e.g. "Username", "Name"). Each sheet needs exactly one.
* **Response** — columns containing the text you want to analyze (e.g. question responses, discussion posts). You need at least one response or segment column per sheet.
* **Segment** — columns containing grouping information that will be applied as segments to your participants (e.g. "Member Tags", demographic categories).
Leave metadata columns like "CreatedAt" timestamps toggled off to keep your data clean.
### Use the summary bar
The summary bar below the sheet name shows how many participant, segment, and response columns you have selected. Click the dropdown arrow on any summary chip to deselect columns in bulk, or to select all remaining unmapped columns as response columns.
Toggle **Hide ignored** to collapse columns you have not included. This is useful for wide spreadsheets where only a few columns are relevant.
### Check sheet readiness
A sheet is ready to import when it has one participant column and at least one response or segment column. The tab for each sheet shows its status:
* A green check mark means the sheet is ready
* An amber warning icon means the sheet still needs column mapping
If a sheet is not ready, an alert at the top of the preview tells you what is missing: "Select one participant column and at least one response or segment column."
### Work with multiple sheets
If your xlsx workbook has multiple sheets, use the tabs to switch between them. Each sheet is configured independently. Sheets that are not fully mapped are automatically skipped during import.
## Import
The footer shows how many sheets are ready and how many will be skipped. Click **Import N sheets** to start the import.
## Speaker merging
Participants with the same name across different sheets are merged into a single speaker. Make sure participant names are consistent across sheets if your data is spread across multiple files.
## Common formatting problems
These examples use xlsx files, but the same rules apply to CSV files.
The first row must contain column titles, followed immediately by participant responses on the next row. Remove any extra rows (task numbers, descriptions, metadata) that sit between the header and the data. Merge task descriptions or question prompts into the column header itself.
### Task numbers in the top row
### Metadata or descriptions in the spreadsheet
### Question / prompt and its description spread across 2 rows
# Video & Audio
Source: https://docs.coloop.ai/docs/file-formats/video-audio
CoLoop works best with high quality audio or video files to deliver transcripts. This guide will walk through how to upload these files, supported formats, best practices, and language support for transcription and translation.
## Supported File Formats
CoLoop supports a range of different video and audio formats. The following table outlines the list of support file types, click the dropdown to view:
| Supported audio file types | Supported video file types |
| -------------------------- | --------------------------- |
| .3ga | .webm |
| .8svx | .mts, .m2ts, .ts |
| .aac | .mov |
| .ac3 | .mp2 |
| .aif | .mp4, .m4p (with DRM), .m4v |
| .aiff | .mxf |
| .alac | .mkv |
| .amr | |
| .ape | |
| .au | |
| .dss | |
| .flac | |
| .flv | |
| .m4a | |
| .m4b | |
| .m4p | |
| .m4r | |
| .mp3 | |
| .mpga | |
| .ogg, .oga, .mogg | |
| .opus | |
| .qcp | |
| .tta | |
| .voc | |
| .wav | |
| .wma | |
| .wv | |
We strongly recommend uploading audio or video files when possible to guarantee reliable format and quality. Transcription quality is dependent on audio, but uploading videos make it easier to see nuances, create clips, and are also important if you are [concept testing with a deck](/docs/concept-testing/stimulus-deck-concept-testing).
* There is a limit of **5 GB per audio file** - you can cut your files into multiple parts or compress the file.
* There is a limit of \*\*8 GB per video file \*\*- use lower resolution video to speed up transcription time and if it is not imperative to the project.
* Once your file(s) has finished uploading press "Complete" and provide additional information to finish transcribing. See how to create transcripts [here](/docs/setting-up-a-project/create-a-transcript#transcribe-2).
### Best practices for recording audio and video
If you have to use a facility be sure to run a sound check before or bring your own recording device.
When recording audio and video it's important to ensure the following:
* **Speakers are clearly audible**: Use high quality, ideally directional microphones and position them in front of the people speaking.
* **One interview per file**: Make sure there is one interview per audio / video file. If you have multiple combined you should cut them into individual interviews before uploading to CoLoop.
### Zoom, Teams, Google Meet Integration
* You can now directly invite CoLoop Recorder to join your calls conducted over Zoom, Teams and Google Meets.
* This allows you to add CoLoop directly to your meeting tool and stream audio directly back to the platform after the call concludes.
* This allows us to make use of the implied audio channels and identify all speakers with near perfect accuracy.
* For guidance, please refer to this document [here](/docs/recording-live-interviews/getting-started).
## Supported Languages and Accents
CoLoop supports near-human accurate transcription from Audio and Video in a range of accents and formats. View our full list of supported languages for transcription [here](/docs/setting-up-a-project/supported-languages).
### Translating your file post transcription
CoLoop offers translation options for any non-English transcript! All of your analysis and quotes will be in English.
* In order to translate your transcript into English, open a transcript, click on the three dots next to the file name, and press ‘Translate transcript.'
* If you'd like to get the transcript back to the original language simply click on 'Reset transcript'.
* You can also bulk select transcripts from the Files tab, then open 'Actions' in the bar that appears at the bottom of the screen (or press ⌘K, Ctrl+K on Windows) and choose 'Translate'.

## Simultaneous Translation
SimTran recordings can be difficult to work with as they contain only one speaker. Information about who is speaking and their role in the conversation is lost and has to be inferred by CoLoop based on the context. If you are conducting Non-English language studies we recommend:
* Transcribing and analysing in the native language if possible
* Asking your SimTrans service to provide transcripts with labelled speakers in [this format](/docs/file-formats/docx)
* Labelling the single speaker in a SimTran transcript as `Moderator / Participant (translated)` and the role to `Participant` (see below).

You might notice some superficial errors or red highlighted words in your transcripts. You can correct errors or edit transcripts as needed by following this [guide](https://coloop-knowledge-base.help.usepylon.com/articles/4559730024-how-do-i-fix-errors-in-my-transcript).
## Video Blurring
Blurring a video permanently hides faces or other sensitive visual content. The blurred version becomes the only copy served anywhere in CoLoop: playback, clips, reels, and exports. The unblurred original is **deleted** when the blur completes. Transcripts and audio are not affected.
Blurring is permanent and cannot be undone. Concept testing needs the
original footage, so it is unavailable for blurred videos.
### Blur an entire video
1. Open a video file from the **Files** tab.
2. Click the **actions menu** (three dots) next to the file title.
3. Select **Blur video**.
4. Select **Entire video** and click **Blur permanently**.
The file shows **Blurring video** while processing. A 10-minute video takes around 30 seconds; longer videos may take several minutes. Once complete, the video player shows the blurred version.
### Blur specific regions
To blur only part of the frame (for example, one participant in a group call):
1. Select **Blur video** from the actions menu.
2. Choose **Only regions I draw on the video**.
3. Click and drag on the video preview to draw red rectangles over the areas to blur. Hover a region to reposition or remove it. Use the playback controls to verify placement.
4. Click **Blur permanently**. The drawn regions are blurred for the full duration of the video. Areas outside the regions remain unchanged.
### Clips and reels from blurred videos
Clips and reels created before the blur were cut from the unblurred video, so CoLoop withholds them until they have been rebuilt from the blurred version.
* **Clips** are re-rendered from the blurred video automatically. They cannot be played or downloaded until that finishes.
* **Reels** containing those clips are marked out of date and must be exported again. You cannot export or download a reel while any of its source videos is being blurred.
If a reel is shared publicly, its link stops working while the blurring runs and stays paused afterward until you export the reel again, at which point the same link resumes, now serving the blurred version. The reel shows a **Public (paused)** badge in the clip library while this is the case. To revoke a link instead of letting it resume, select **Stop sharing reel** from the reel's menu. See [How to share a reel](/docs/analysis/creating-clips#how-to-share-a-reel).
To blur only a reel's export, leaving the source video untouched, open the **Reel Editor** and toggle **Blur video** in the header.
### Coming soon
* **Automatic face detection**: automatically detect and blur faces without drawing regions manually.
* **Organization-wide blurring policy**: enforce automatic blurring on all uploaded videos across your organization.
Interested in early access? Reach out to [support@coloop.ai](mailto:support@coloop.ai).
# Concept & Message Testing
Source: https://docs.coloop.ai/docs/getting-started/concept-testing-mode
These guides cover how to work with stimulus for ad, concept, or product testing in CoLoop, outlining best practices and direct you to the relevant guidance for your specific study type.
Concept testing projects are particularly challenging for AI tools as they often struggle to disambiguate similar concepts. CoLoop features a specialised concept testing mode that can be enabled during project setup.
## What does concept testing mode do?
Concept testing mode enables you to enter a list of concepts, brand names or any other key phrase during the project setup. The AI will automatically label text segments where they appear and even track when the conversation changes from discussing one to another.
* These will appear in the transcripts and evidence panel
* Concepts entered here will be passed into the Key Phrases section when transcribing any audio or video files.
## How does it work?
CoLoop supports two different concept testing methods, designed to fit different study designs and data collection methods.
1. Concept Testing with No Stimulus Deck: Use this method when you are collecting data in person, don't have access to video, or are presenting dynamic concepts online (e.g. figma or a website).
2. Concept Testing with a Stimulus Deck: Use this method when you are collecting data online and will be showing the concepts on a stimulus deck while screen sharing. CoLoop detects each slide in your recordings automatically, so the deck needs no tagging or labeling.
Both of these methods require a bit of planning prior to data collection, so please read the relevant guidance before data collection begins. This will ensure you have the smoothest experience and will increase concept detection accuracy.
Use when are collecting data in person, don't have access to video, or are presenting dyanmic concepts online (e.g website or figma).
Use when you are collecting data online and will be showing the concepts on a stimulus deck while screen sharing. Upload the deck exactly as you presented it.
For studies that require multiple stimulsu decks, such as multi-market. Use when you are collecting data online and will be showing the concepts on a stimulus deck while screen sharing.
# Introduction
Source: https://docs.coloop.ai/docs/getting-started/introduction
CoLoop helps Insight & Strategy teams complete content analysis 10x faster, cheaper and more accurately
Here you will find guides on how to setup a project, key use cases and best practices. Please reach out to [The CoLoop Team](mailto:support@coloop.ai) for any questions or feedback.
If you haven't used CoLoop on a project yet, we **strongly** recommend booking a kick off call [here](https://www.coloop.ai/book-a-demo).
### What is CoLoop?
CoLoop helps researchers analyze qualitative data by automatically surfacing patterns, themes, and sentiment across transcripts, recordings, and open-ended responses.
It links insights directly to source material for easy verification and allows users to organize findings in customizable analysis grids.
For reporting, CoLoop makes it easy to extract key quotes, create video and audio clips, and export toplines or structured outputs that can be directly used in presentations and reports.
Ready to jump straight in? Click on one of the quick start guides below
## Getting Started Guides
Upload transcripts, audio, or video files to transcribe and analyze interviews or focus groups
Import diary, ethnography, bulletin board or other online qualitative data from a range of platforms
Compare and contrast reactions to different concepts, territories, stimulus or products.
Tips and tricks for getting the most out of qualitative data from across different markets and languages
# Live Interviews
Source: https://docs.coloop.ai/docs/getting-started/live-interviews
Here, you'll find best practices and guidance on setting up a projects involving live interviews using CoLoop. Learn how to record your interviews in CoLoop, or turn raw audio and videos into transcripts within minutes.
Uploading your live interviews to CoLoop ensures accurate transcripts, speaker recognition, and richer insights. By capturing real voices and tone, CoLoop delivers deeper analysis and more natural summaries. Adding project context through a discussion guide will help refine results and highlight key themes. You’ll also be able to create clips and reels that bring your research to life.
## Recording Interviews
For projects where you're conducting interviews or focus groups via Zoom, Google Meets, Microsoft Teams, or Webex, invite the CoLoop recording bot to seamlessly record and upload your sessions. The recorder feature allows for the highest accuracy of speaker recognition by distinguishing different voice streams in calls. You'll be able to create and keep recordings securely within your project, and plan ahead for CoLoop to join and record your calls.
Learn how to let CoLoop record and upload your interviews [here](/docs/recording-live-interviews/getting-started).
## Uploading Interviews
You can also upload high quality audio or video files. You'll be able to get the full CoLoop experience and receive accurate transcripts in over [100 supported languages](/docs/setting-up-a-project/supported-languages). CoLoop also supports English translation from any transcript. Raw video and audio also allows you to create compelling clips and reels within the platform.
After uploading audio or video CoLoop will prompt you to enter...
* Estimated numbers of speakers (both moderator and respondents)
* Language or accent details (choose spoken language and you can translate afterwards)
* Keywords for specific brands or products that are retained throughout the project (make sure you hit the enter key after each)
Providing these details (especially keywords!) will help to improve the transcription accuracy.
## Uploading a Discussion Guide
A discussion guide, project or client brief, or a contextual document with information about your project will help to inform CoLoop. CoLoop will use this information to automatically generate objectives and a description. Uploading this guide will help to articulate top-line summaries and Q\&A guides for each project file. This will also allow you to populate analysis grids and chats with suggested questions in analysis.
| Section | Example |
| --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Project Description | “This project is exploring different concepts encouraging people in the UK to quit smoking” |
| Methodology | “The project involved discussions around how simple, unexpected, concrete, credible, emotional, motivating and how much storytelling there was within 3 different concepts” |
| Description of any stimulus | Concept 1: a pair of lungs made from a wilted flower on the left side, and a vibrant, colorful bouquet of flowers on the right side. The text reads “QUIT SMOKING AND BREATHE” |
| | Concept 2: features a handwritten note saying, “I’m not scared of spiders. I’m scared of my Mum dying from smoking,” next to a real spider. It also includes a statistic about the number of people dying each week in the UK from smoking-related diseases. |
| | Concept 3: shows a diseased, decomposing part of the body inside a cigarette paper, with the text: “Every cigarette rots you from the inside out.” |
| Overall Objectives | “The project aims to understand which of these concepts is the most motivating for quitting smoking, and how much the sticky ideas framework (simple, unexpected, concrete, credible, emotional, storytelling) impact motivation.” |
## Concept Testing
CoLoop can recognize and help you analyze different stimulus, concepts, or message testing projects.
Please refer to [these guides](https://coloop-knowledge-base.help.usepylon.com/collections/5060845168-concept_testing) to find the best concept testing flow for you.
## Other Supported File Types
* [**Transcripts**](/docs/file-formats/docx): We recommend using these if you are working in a language we don’t support yet or have gold standard human written or curated transcripts available. DOCX and TXT transcripts will import with the speaker names you assign them with.
* [**Spreadsheet (xlsx)**](/docs/file-formats/excel): These can be used to automatically apply segments or upload corresponding interview notes alongside your raw data (read more about this here.)
### Recommended Guides
This article outlines the key differences between the AI chat and analysis grid and explains when to use one or the other.
Understand how to write a good project description to augment your analysis and get the most out of CoLoop.
This article covers further details on how CoLoop works and some techniques for writing effective prompts
# Multimarket studies
Source: https://docs.coloop.ai/docs/getting-started/multi-market-studies
This article outlines supported languages, best practices and further information for researchers conducting multi market studies.
CoLoop provides robust support for multi-market studies, enabling teams to work across multiple languages, regions, and participant segments.
CoLoop offers transcription for 100+ languages for Video, Audio and Community Data files with the option to translate to English where required. Transcripts can be uploaded and analysed in their original language, with translation options available where needed.

Add segments to compare insights across markets, identify consistent themes, and explore cultural or contextual differences. All data sits within a single project, so users can choose to zoom in one market or get the bigger picture with cross-market analysis.
For best practice on setting up your multi-market study, and more information on support languages and simultaeneous translation, please follow the guidance [here](/docs/setting-up-a-project/setting-up-multi-market).
# Online Qualitative
Source: https://docs.coloop.ai/docs/getting-started/online-qual
CoLoop supports the analysis of qualitative data from Excel files and many online community data platforms. Whether you’re running a small online community or a global study, CoLoop helps you bring structure and clarity to every conversation.
CoLoop connects with your go-to qual platforms so you can import projects instantly. Browse the guides below to download a CoLoop-ready export and dive into your analysis.
## Analysing Online Qualitative Data
CoLoop is built to handle all kinds of online qual projects, from communities to bulletin boards. These projects often look a little different from interviews or focus groups because they tend to be:
* **More structured:** split into specific tasks and activities
* **More segmented:** include multiple subgroups and participant types
* **More extensive:** involve larger participant numbers
* **More diverse:** combine text, audio, video, and other media
See more on analysing community data [here.](/docs/analysis/basic-grid#analyzing-community-data)
# Uploading Additional Waves of Data in Open Ends
Source: https://docs.coloop.ai/docs/open-ends/additional-waves
Additional waves let you grow your dataset over time - perfect for longitudinal studies or follow-up surveys, without creating a new project.
### Critical Rule for Multiple Waves
Either the questions or the respondents must stay the same between waves.
* **Example A (Same Respondents, Different Questions):**
* You interview the same group right after an event and again six months later with **new questions**.
* **Example B (Same Questions, Different Respondents):**
* You repeat the same survey questions with a **new participant group**.
This ensures CoLoop can correctly align your new data with your existing project.
### Preparing and Uploading Your Additional Wave
Upload your file with the **same column headers and structure** as your first upload.
* **Unique IDs**:
* If re-interviewing the **same respondents**, use the same **Respondent ID** values as in Wave 1.
* For new respondents with the same questions, assign **new unique IDs**.
* **Avoid Duplicates**: Only include *new* responses—duplicates could overwrite or cause errors.
**Open your existing Open Ends project.**
1. Click ‘Uploads’ and select ‘Import Data.’
2. Select your .xlsx file.
3. Assign each field to the correct column (Respondent ID, Question, Answer, Segments, etc.).
4. Review and confirm—double-check that your consistent element (**questions** or **respondents**) aligns with Wave 1.

### After Uploading
* **Verify Merged Data:** Check your project dashboard to confirm the new responses are integrated.
* **Refresh Analysis:** Rerun any analysis or tagging workflows to include the new data.
* Keep in mind the codebook will not be edited or changed by new uploads.
### Download an Uploaded File
1. Open your existing Open Ends project.
2. Click **Uploads**.
3. Click the download icon to the right of **Open** for the file you need.
Your browser downloads the original `.xlsx` file. The download remains available if data import fails, as long as the source file finished uploading.
# Excel Formatting for Open Ends
Source: https://docs.coloop.ai/docs/open-ends/excel-import-format
This guide explains how to map your data before importing into CoLoop’s Open Ends tool. Find the best ways to format different types of open ended response data (e.g. survey, conversation, and chatbot data) as well as see downloadable examples for each data type. Below, you’ll learn best practice tips and common pitfalls to avoid.
### Why Mapping Matters
CoLoop’s Open End Analysis tool is designed to handle diverse data from various sources efficiently regardless of formatting. You are now able to simply select your corresponding columns to the corresponding fields in the dropdown menu. See more on auto-mapping [here](/docs/open-ends/open-ends-project-set-up). This works particularly well for survey data.
For more complex data e.g. chatbot data, please adhere to the standardized format outlined below to ensure your data is processed accurately. This approach allows us to provide a consistent, high-quality analysis experience for all users.
### **File Requirements**
* File format: .xlsx (Excel)
* Maximum responses: 10,000
Example: *10 respondents × 10 questions = 100 responses* (only the response cells count).
Files exceeding 10,000 responses will trigger an error. Contact support if your use case exceeds this limit.
## Data Types
### **Question Data (Survey-Style)**
Use this when you have **survey questions and answers**.
**Required columns:**
* **“Respondent ID”:** Links each response to a participant.
* **“Question Columns”:** Each column header is a question; each cell contains an open-ended response.
**Optional columns:**
* **\[Tag] / \[Tag] TagName:** Labels applied to responses for that participant(e.g., “Satisfaction”, “Round 1”).
* **\[Segment] / \[Segment] SegmentName:** Additional demographic or group info for filtering.
While this is optional, having your data formatted like this before importing allows CoLoop to detect these automatically.
*Example:*
| Respondent ID | What improvements would you suggest? | \[Tag] Satisfaction | \[Tag] Survey Round | \[Segment] Customer Type |
| :------------ | :----------------------------------- | :------------------ | :------------------ | :----------------------- |
| R001 | Add more integrations | Very satisfied | Round 1 | New |
| R002 | Improve Wi-Fi connectivity | Somewhat satisfied | Round 1 | Returning |
### **Conversation Data (Chatbots & Transcripts)**
Use this for **chatbot interactions or interview transcripts with multiple turns**.
**Required columns:**
* **“Respondent ID”:** Matching the ID from the Respondent Data sheet
* **“Question”/”Answer” Columns:** During import, select the respective “Question” and “Answer” columns via the dropdown menu.
**Optional columns:**
* **“Turn Number”:** This represents the order of conversation turns. If a respondent appears on multiple rows, CoLoop assumes their turns are ordered from top to bottom on your sheet Sequential conversation turn (start at 1).
* **\[Tag]:** Apply labels to each turn (e.g., “Positive”).
* **\[Segment]:** Add segmentation (e.g., “Device”).
*Example:*
| Respondent ID | Turn Number | Question | Answer | \[Tag] Sentiment | \[Segment] Device |
| :------------ | :---------- | :----------------------- | :--------------- | :--------------- | :---------------- |
| R001 | 1 | How was your experience? | It was great! | Positive | Smartphone |
| R001 | 2 | What did you like most? | The quick setup. | Positive | Smartphone |
### **Respondent Data (Demographics & Segments)**
You can also upload demographic information about participants.
**Required column:**
* **“Respondent ID”:** Unique ID for each participant.
**Optional columns:**
* **“Respondent Name”:** Participant’s name.
* **\[Segment]:** Demographics or grouping variables.
*Example:*
| Respondent ID | Respondent Name | \[Segment] Age | \[Segment] Gender |
| :------------ | :-------------- | :------------- | :---------------- |
| R001 | John Doe | 25–34 | Male |
| R002 | Jane Smith | 35–44 | Female |
## Excel Structure Overview
There are **two main ways** to format your excel files depending on how your study is structured.
**Option 1: Combine Respondent and Response Data in One Sheet**
**Best for:** Simple studies with one sheet of responses per file (such as open ended responses from surveys).
In this format, every row contains **both the response and the respondent’s segment (demographic) information**.
**Option 2: Separate Respondent Sheet + Question Sheet**
**Best for:**\
Studies with multiple sheets of responses (e.g. one sheet per product or condition), or when doing within-participants testing.
**In this format:**
* You include a **Respondent Info sheet** with metadata like age, gender, or market segment.
* Each **Question/Response sheet** contains open-ended feedback, **linked by Respondent ID**.
# Downloadable Examples
## Open Ended Survey - One Sheet
This sheet is an example of the Option 1 formatting style, where respondent information and open-ended responses are combined in a single sheet.
[Download Here](https://coloop-public.s3.eu-west-2.amazonaws.com/open-ends/example-data/example-open-ends-survey-data-one-sheet.xlsx)
*Example data is a simple open ended survey about the taste and texture of crisps.*
## Open Ended Survey - Respondent & Question Sheet
This sheet is an example of the Option 2 formatting style, where respondent information and response data are stored in separate from sheets.
[Download Here ](https://coloop-public.s3.eu-west-2.amazonaws.com/open-ends/example-data/example-open-ends-survey-data.xlsx)
*Example data is a simple open ended survey about the taste and texture of crisps.*
## Open Ended Conversation Data (Between Participants)
This sheet is an example of open ended conversation data, so each respondent has multiple turns. Respondent information and response data are stored in separate from sheets for clarity.
[Download Here](https://coloop-public.s3.eu-west-2.amazonaws.com/open-ends/example-data/example-open-ends-conversational-data-between-participants.xlsx)
*Example data is a chat-bot conversation where each participant responded to a series of questions about their experience using a specific painkiller. This is a between-participant example so participants trialled either Ibuprofen or Paracetamol.*
*Each participant had 5 conversation turns about their experience, with responses tagged by the product (e.g., Paracetamol, Ibuprofen).*
*The respondent data sheet contains demographic segments; they enable analysis by user group.*
## Open Ended Conversation Data (Within Participants)
This sheet is an example of open ended conversation data, so each respondent has multiple turns. Respondent information and response data are stored in separate from sheets for clarity.
[Download Here](https://coloop-public.s3.eu-west-2.amazonaws.com/open-ends/example-data/example-open-ends-conversational-data-within-participants.xlsx)
*Example data is a chat-bot conversation where each participant responded to a series of questions about their experience trying 4 different chocolate products. This is a within-participants example so participants all tried and answered questions about all 4 chocolate bars.*
*Each product has its own sheet which contains the conversation data per product and a \[Tag] for that product, and a separate respondent data sheet includes participant demographics.*
## Best Practices and Tips
1. **Focus on Open-Ended Data**: Ensure that your Excel file only includes open-ended questions and responses. Close-ended questions should be formatted as tags or segments instead.
2. **Data Cleaning**: Before import, thoroughly clean your data:
* Remove any fully blank rows or columns
* Ensure consistent formatting across cells
* Check for and remove any hidden sheets or data
3. **Validate Respondent IDs**: Use Excel's data validation tools to ensure Respondent IDs are unique and consistent across sheets.
4. **Check Turn Numbers**: For Conversation Data sheets, verify that Turn Numbers start at 1 and increment sequentially for each Respondent ID.
5. **Use Clear Naming Conventions**: Choose descriptive names for your segments and tags to facilitate analysis.
6. **Keep It Simple**: If a column doesn't apply to your data, leave it out rather than including empty values.
7. **Review Before Import**: Double-check your file for accuracy and completeness before attempting to import it into CoLoop.
## Common Pitfalls to Avoid
1. **Mixing Open and Closed-Ended Data**: Don't include closed-ended questions as separate columns. Instead, use tags or segments to represent this information.
2. **Inconsistent Respondent IDs**: Ensure that Respondent IDs match exactly across all sheets where they appear.
3. **Non-Sequential Turn Numbers**: In Conversation Data sheets, make sure Turn Numbers are sequential without gaps for each Respondent ID.
4. **Exceeding Response Limit**: Remember that projects with more than 10,000 responses will by default trigger an error.
5. **Using Unsupported File Formats**: Only .xlsx files are supported. Convert your data if it's in a different format.
6. **Incomplete Data**: Ensure all required columns are present in your sheets.
7. **Inconsistent Naming**: Use the exact column headers specified in this guide, including the brackets for \[Tag] and \[Segment] columns.
By following these guidelines, you'll ensure that your data is correctly formatted for import, enabling smooth and accurate analysis of your open-ended responses.
If you encounter any issues or have questions about formatting your data, please don't hesitate to reach out to our support team.
# Analysing Open Ends Data
Source: https://docs.coloop.ai/docs/open-ends/open-ends-analysis
This document will walk you through how to analyze your open ended data using the CoLoop Open Ends tool. It will cover how to understand the final codebook, how to use the analysis grid and insights features, and how to export your data.
### Analysis & Output - Explore your Data
Explore your data by either creating insights, using the grid view, or take your analysis offline by exporting the data.
You can also check the final version of your codebook at anytime, and remind yourself what each theme, sub-theme and code means.
### Insights
Visual your data using insights. Created insights focusing on specific questions, segments, tags and sentiments using the filter function.

Additionally, you can query the data and ask CoLoop questions about the data.

### Grids
Analyse and explore your data using the grid view.

CoLoop will display all codes in descending order based on the number of open-ended responses assigned to each one. If sentiment analysis was applied, this will be shown at the bottom right of each theme. To view the sentiment count, users can hover over the sentiment bar with their mouse.
Users can choose to customise how they view their data by selecting a filter as shown below. You can add multiple filters.
CoLoop will output a column for each sets of filters applied. Shown below, from left to right, are analysis columns showing a sentiment filter and a participant segment filter. Users can choose to display response numbers in either raw count or by percentage, as shown on the right hand side of the image below.

### Evidence Panels
To inspect evidence, users can click on a theme which will prompt an evidence panel to open up on the right hand side of the screen, as shown below.

### Exporting Open Ends Analysis
Users can easily export their open ends analysis to xlsx. format. Users can export the whole grid, by selecting the export button found on the left of the analysis dashboard, as shown below.
Alternatively, users can export individuals columns by clicking on the three dots at the top of each column as shown below.
Users can export the whole grid to Excel format by selecting "Export" and then "Grid", as shown below. This output will produce an excel document which will list out all of the themes along with number of associated participants, responses and sentiment.

Alternatively, users can export the raw data to excel files, in several formats.
The compact export option will provide users with an Excel sheet with three tabs, the first with the codebook, the second with a respondents list, and the third with each respondent's open ended responses and their associated codes and sentiments, as shown below.

Alternatively, the Expanded export option will provide users with a more granualr breakdown which can be be easily used in further data analysis.
Expanded export options explained:
* Expanded Only: Will produce an output that contains a code-by-code breakdown of how each open-ended response was coded in a binary format; 1 indicating the presence of a code for that response, and 0 indicating its absence.
* One row per conversation: All conversation turns for the same participants will be in the same row with an averaged (mean) sentiment and aggregated codes. (Only applicable to ChatBot data).
* Include "Uncoded" theme: This will add an uncoded theme at the end of the excel file which indicates which open ends have no associated codes.

# Setting up an Open Ends Project
Source: https://docs.coloop.ai/docs/open-ends/open-ends-project-set-up
This guide will walk you through how to set up a project in Open Ends — a powerful tool designed to help you analyze up to 10,000 open-ended responses at a time. It will cover creating a project, generating the codeframe, and applying sentiment analysis.
The Open Ends tool will generate a codeframe that applies to all of the responses within your uploaded data (i.e. one codeframe for all open ended questions). If you would like discrete codeframes per individual open ended question, please create an individual project for each question instead.
### Creating an Open Ends Project
Click 'Create Project' in the top right corner of your screen. In the pop-up window, be sure to select 'Open Ends'—it will appear greyed out, indicating it's selected.
### Upload Your Data
After creating a new Open Ends project:
* Upload up to **10,000 open-end responses** in **.xlsx** format.
* Example: *10 respondents × 10 questions = 100 responses* (only the response cells count).
* Please review [**Formatting Guidelines**](/docs/open-ends/excel-import-format) to ensure CoLoop can read your files correctly.
### Assign Columns to Fields
Once your data is uploaded, match each field to the appropriate column. You can also select which columns to import.
| **Field** | **Description** |
| :------------------- | :--------------------------------------------------------------------- |
| **Respondent ID** | A unique ID that identifies each respondent. |
| **Open Ends** | The open-ended question text or label. |
| **Segments** | Demographic or segmentation data (e.g., age group, location). |
| **Participant Name** | The name of the participant (optional if Respondent ID is sufficient). |
| **Response Tags** | Tags applied to all responses from that respondent. |
| **Question** | The specific question that was asked. (Chatbot data only) |
| **Answer** | The respondent’s provided answer. (Chatbot data only) |

### Creating the Codebook
You have two options on how to begin creating your codeframe.

**Import from Excel**
If you already have an idea of what your codeframe should look like, you can upload an initial codeframe from Excel.
Please find a downloadable formatting example[ here](https://coloop-public.s3.eu-west-2.amazonaws.com/open-ends/example-data/example-codeframe-2.xlsx).
**Auto-Initialise the Codebook**
Alternatively, you can auto-initialise and CoLoop will generate the initial iteration of the codebook for you.
### Generate the Codebook
CoLoop will generate an initial iteration of the codebook by sampling from a sub-section of your data. You can now work with the tool to refine the codebook further.

You can explore the meaning of each theme, sub-theme, and code simply by clicking on it. CoLoop will then display the inclusion criteria (i.e., what characteristics or elements must be present for an open end to be categorized under this theme or code) and the exclusion criteria (i.e., what characteristics would disqualify an open end from being included in this category). You’ll also see a selection of sample quotes that illustrate how open ends are grouped within each theme or code.
### 
### Refine the Codebook
Generate and edit detailed, nuanced code frames with clear criteria aligned to your objectives for deep actionable results.

You can refine your codeframe several ways:
**Across the whole codeframe**
* By typing in a general instruction in the chat box at the bottom of the screen.
* You can directly click on themes and codes and drag and drop them to a new location within the codeframe.
**On an individual theme level, by clicking on three dots next to a theme**
* \*\*AI Expand: \*\*This will refine and enrich the codeframe by introducing more specific and nuanced codes that sit within the same thematic family, helping you capture subtler distinctions in the data.
* \*\*AI Modify: \*\*This will open a dialogue box where you can directly suggest changes. For example, you might update the inclusion or exclusion criteria, or ask the tool to generate additional codes that fall under the selected theme.
* \*\*Change Theme Label: \*\*You can rename the theme as needed.
### Understanding Iterations
Every change you make to the codeframe automatically generates a new iteration, allowing you to track its evolution over time. You can identify which codes have been updated in the current iteration by the coloured dots that appear beside them (outlined in red below).
You can check which iteration of the codeframe you are on at the bottom left of the screen (outlined in blue below). You can easily toggle between iterations by clicking on the arrows.
### 
### Finalizing your Codeframe
When are are nearly finished refining your codebook, we suggest rotating your sample by selecting **'Rotate sample'** at the bottom of the screen (outlined in red below). This will apply the current iteration of the codeframe to a new and different sub-set of your data, to ensure robustness of the codeframe across your data.
You can also enhance your codeframe automatically by selecting **‘Auto-enhance’** at the bottom of the screen (outlined in blue below. This feature prompts CoLoop to review your codeframe and refine it—such as by removing redundancies or streamlining overlapping codes—to improve clarity and structure.

To finalise your codeframe, make sure your desired iteration is visible on the screen (outlined in red below), then select 'Next' in the bottom right hand corner and confirm. Please note, that CoLoop will finalise whichever version of the codeframe is selected and visible on the screen.
### Start Analysis
Users are then prompted to start the analysis.
### 
# Recording Using CoLoop
Source: https://docs.coloop.ai/docs/recording-live-interviews/getting-started
This guide will introduce the CoLoop Recorder, and describe how to capture your online interviews and focus groups when recording with Zoom, Google Meet, Microsoft Teams or Webex.
Instead of having to run an interview, save the file, and then manually upload it to CoLoop, our system offers a recording bot service. The bot joins your meeting as a participant and quietly listens in the background. When the meeting ends, the video or audio recording is automatically sent to CoLoop — no manual upload required!
To capture and record interviews live as they are conducted, CoLoop can be integrated directly with:
* [Teams](/integration/integration/teams)
* [Zoom](/integration/integration/zoom)
* [Google Meets](/integration/integration/google-meet)
* [Webex](/integration/integration/webex)
This can help streamline research ops and will also significantly improve speaker accuracy particularly when conducting focus groups with multiple participants.
There are **two easy methods** to add CoLoop to your calls:
* Use +Join to invite the recorder with a meeting link
* Create a project-specific email address to add to your calendar invites
The status of the recorder bot is visible in the **Meetings** tab so you can track its progress. Once the file is automatically uploaded to CoLoop, it will appear in the **Files** tab where it can be transcribed and prepared for analysis.
**Important:**
* Please read the specific guidance document for the platform you are recording with prior to using the meeting recorder.
### Join Meeting Button
To invite the recording bot to a meeting that is start, follow these steps:
1. Navigate to the **Meetings** section in CoLoop.
2. Select + **Join Meeting**.
3. Paste in your Zoom, Teams, Google Meets or Webex meeting invite URL (the same URL you’d share with a participant).
**Meeting Starting Soon**
For a meeting starting within 10 minutes or that has recently started please select 'Now'.
**Schedule Meeting For Later**
For a meeting starting later or in the future select 'Later' and then enter the date and time of the meeting. Please note the time shown will always match the timezone of your device.
### Project Email Invite
Users can also create an email address for specific CoLoop projects and add that email to all associated calls.
This method is ideal for adding CoLoop to multiple meetings or for allowing third parties to schedule calls by using the project-specific email.
1. Navigate to the **Meetings** section in CoLoop.
2. Select **Email Invite** and create an email address for the project.

3. Once the project email address is created, copy it and add it to all call invites.
4. All scheduled meetings will be displayed in the **Meetings** section. This method can be used to arrange the CoLoop recording bot well ahead of the interview time.
# Troubleshooting
Source: https://docs.coloop.ai/docs/recording-live-interviews/troubleshooting
Learn how to troubleshoot issues with the CoLoop recording bot.
Below are some common issues and tips to resolve them.
## Bot did not join a zoom meeting
**Microsoft overrides Team Link**
This issue is likely due to the **Teams meeting** toggle being switched on in your Microsoft Calendar invite. When the toggle is on, Microsoft overrides your Zoom URL with a Teams URL. As a result, the bot will attempt to join a Teams meeting instead of your intended Zoom meeting.
**Zoom Webinar Requiring Registration**
The CoLoop recording bot can only join zoom webinars which do not require registration.
**Zoom Sign-In Required**
CoLoop can join zoom meetings bwhen sign-in is required as long users enable this in meeting bot settings. Meeting bot setting can be managed at the organisation level by a workspace admin, or on the project level by a project admin.
**Timezone Settings**
If CoLoop didn’t join a scheduled call, it may be because the meeting time was entered in a different timezone. The +Join Meeting method always uses the timezone of the user's device it was scheduled on.
# Confirming speakers
Source: https://docs.coloop.ai/docs/setting-up-a-project/confirming-speakers
How to confirm speaker names and roles across a file, a selection, or a whole project, and what happens when two speakers in one file share a name.
When a transcript is added, CoLoop labels who is speaking. A speaker who
introduces themselves, or who someone addresses by name, lands confirmed.
Anything less certain starts unconfirmed and waits for you. Confirming tells
CoLoop the names and roles are right, and files with confirmed speakers are
the ones that flow into analysis.
You can confirm speakers one at a time from the files view, or confirm a whole
batch in one action.
You may see speaker names suggested from the file name, from speakers already
named on the project's other files, or for meeting bot recordings from the
meeting's participant list. A suggested name stays unconfirmed until the
transcript clearly identifies the speaker or you confirm it.
## Confirming a batch
Open **Confirm speakers** from a file's row to confirm that file. To confirm
several files at once:
1. Select the files. To do a whole project, select every file with the
checkbox in the table header.
2. Click **Confirm speakers** in the bar that appears at the bottom of the
screen, or open **Actions** there (⌘K, Ctrl+K on Windows) and choose it.
Most of the time this just runs, and a message tells you how many speakers
were confirmed. CoLoop stops to ask first only when something will happen
that you did not ask for:
* a speaker will be renamed to keep it apart from another (see below)
* a speaker has no role yet, so it will be skipped
In those cases you get a summary of exactly what will happen, and nothing is
written until you confirm. Files whose speakers are already confirmed are
left untouched.
## Speakers who need a role first
A speaker with no role yet cannot be confirmed, because a missing role is
exactly what still needs review. It is skipped and named for you, while every
other speaker in the batch is still confirmed; one unfinished speaker does not
hold up the rest. Give it a role and confirm again to include it.
## When two speakers share a name
Two speakers in the same file can end up with the same name and role, for
example if a transcript names two people "Amelia". Confirming both would make
them impossible to tell apart, so CoLoop keeps them separate by numbering the
later one: `Amelia` and `Amelia (1)`.
This is a rename, not a merge. The two remain separate speakers with their own
turns. The dialog tells you how many will be numbered this way before you
confirm.
Two important cases where this does **not** happen:
* **The same name in different files.** Two files can each have an "Amelia"
and both keep the name. They are separate speakers until you deliberately
merge them from the participants view.
* **The same name in different roles.** A participant and a researcher can
both be called "Ryan" in one file, since only participants are referred to
by name in analysis.
## Confirming a speaker who appears in several files
If you have merged speakers across files, that speaker is one person spanning
several transcripts. Confirming from a file's context applies to that file
only; the speaker's other files are left as they were. This keeps the change
limited to the file you were working in.
# Creating projects
Source: https://docs.coloop.ai/docs/setting-up-a-project/create-a-project
Learn how to create and setup projects in CoLoop for qualitative research. Follow steps to upload research material, generate project descriptions, and optimize transcription for accurate analysis.
## Project setup
* Start by navigating to your CoLoop home space. In the top-right corner, click the **"Create"** button.
* Provide a **descriptive project name** (e.g., "First Time Voters Interviews"). Choose a name that reflects the topic, wave, or type of data so it's easily recognizable.
* Add **project tags** (optional but recommended). These are labels that will help you filter and search for the project later.
* Choose a **data storage region**: US, UK, or Europe. All are hosted on encrypted AWS servers and are equally secure. Select Europe to be GDPR-compliant. Choose the region that best fits your privacy needs. If your organization admin has [enforced a storage region](/docs/collab-and-access-management/data-residency), this is pre-selected and cannot be changed.
## Upload your discussion guide
The Discussion Guide should be in DOCX format and contain examples of the types of questions and discussion points your research focused on. This can also be used to automatically generate a project description (step 4).
If you are not ready to add a discussion guide or project details, click **Skip project setup for now** to proceed to uploading or recording research material directly. You can return to project setup later.

### Enter any additional objectives
These should be the main objectives of your research project. These will be used to generate the project description in (step 4).

### Generate or write a project description based on this information
You can generate this if you've uploaded a discussion guide and provided some objectives or simply write it yourself. This description will serve as the AI's 'long term memory'. It will be used as context when answering any questions.

### What does this do?
* These steps are used to provide context that will be used to improve downstream performance
* They also help to improve transcription with brand names and provide suggested questions in the analysis grid
* We **strongly recommend** providing a description of your project and any other requirements you have in the project description.
* This can **drastically** improve performance when answering questions or summarizing themes.
## Uploading research material
### Transcription (audio and video)
You can download transcripts by clicking `Open` then the 3 dots menu to the right of the title.
Coloop uses state of the art transcription models to convert English audio or video to text. The accuracy of this can be further enhanced by clicking `Continue` and providing the following **optional** information below.
#### 1. Number of speakers
* Enter the *expected* number of speakers in the audio or video
* This includes *anyone* present in the audio e.g. support staff, soundtracks from stimulus material etc.
#### 2. Speaker accent
* We currently offer UK, US, and AU English.
* Choose English with no parentheses to account for global accents, or if your participants are none of the above.
#### 3. Keywords
* Enter any brand names or keywords that appear in your discussion guide - CoLoop is trained on dictionary models so this will tell the tool to look out for atypical and non-dictionary terms.
* The list does not have to be exhaustive - even providing a few can cause dramatic improvements. The list is saved throughout the project.
### Labeling speakers
Once transcribed, CoLoop works out who is speaking and what role they played. A speaker it cannot place keeps its `Speaker A` label for you to name. Names the transcript settles land confirmed; the rest wait for you in [confirming speakers](/docs/setting-up-a-project/confirming-speakers). To rename across many files at once, see [fixing speaker names and roles](/docs/setting-up-a-project/fixing-speaker-naming).
A speaker belongs to the file it was found in. The same name in two files is
two speakers until you merge them; two speakers with the same name and role
in one file are numbered apart, `Amelia` and `Amelia (1)`.
#### Assigning roles to speakers
CoLoop needs to know whether somebody is a `researcher` or a `participant`. This is so that the AI uses comments made by participants as supporting evidence, and researchers as context. `Translator` counts as research-side. `Unknown` means the role has not been settled, and a speaker carrying it cannot be confirmed.
CoLoop can assign these automatically, but it may leave out some that are unclear, in which case you can edit them afterward. Change the role by clicking on the icon next to the speakers name in the transcript. If you aren't sure or it isn't clear choose `participant`.
If you need to edit the speaker names, check out our guides on speaker labeling [here](https://coloop-knowledge-base.help.usepylon.com/collections/8488086775-speaker_labeling).
## Next steps
Once you've set up a project, you're ready to jump into the [analysis grid](/docs/analysis/analysis-grids) or [chat](/docs/analysis/chat-2.0)!
# Uploading data & creating transcripts
Source: https://docs.coloop.ai/docs/setting-up-a-project/create-a-transcript
This document will take you through how to upload files, optimize settings for transcription, label speakers, and utilize additional features like transcript correction and translation to enhance qualitative research efficiency.
You can choose from a wide variety of primary research data types to import directly into CoLoop.
Find more information on supported file types and formatting guidelines to import into CoLoop here:
* [**Audio and Video**](/docs/file-formats/video-audio)
* [**Transcripts**](/docs/file-formats/docx)
* [**Community Data (incling, Qualzy, Recollective & Fieldnotes)**](/docs/file-formats/community-data)
* [**Excel (Survey or Community Data)**](/docs/file-formats/excel)
## Transcribe
## **Import audio and video**
* Upload all recordings **in bulk** to save time. CoLoop will process them in parallel. Transcription time typically depends on file length and size, so use lower resolution video or upload audio to save time.
* Benefits of video and audio include seamless transcription and enables **clipping** features for deliverables
* Make sure your audio or video recordings are **high quality**. We recommend doing this with a video conferencing tool like Zoom or Teams.
* Uploaded files must be under 5 GB each.

### **Transcribe**
Press 'Continue' to start transcribing your files.
* Select the **language** (100+ supported, see [**here**](/docs/setting-up-a-project/supported-languages)) or choose from four English variants (Global, US, UK, Australia).
* **IMPORTANT — Always transcribe the files in their original language. You can translate them into English later.**
* Specify the total **number of speakers** including moderators, up to 10. CoLoop treats it as an expectation, so check the speakers it found afterwards.
* Optional features:
* **Speaker names**: Replace names with codes taken from the file name. Off by default; see [anonymized speaker names](#anonymized-speaker-names).
* **PII redaction**: Automatically anonymize terms like job titles or names.
* **Keyphrases**: Add specific brand names or acronyms to improve transcription accuracy (e.g., “CoLoop”, “MS”, etc.)
* If you are working with files with Simulteanoues Translation, please see the guidance [here](/docs/setting-up-a-project/setting-up-multi-market#simultaneous-translation). However, we strongly recommend uploading the original language recordings if possible.
You can then translate your files as required. For more guidance please see [here](/docs/setting-up-a-project/translation).
### Anonymized speaker names
Tick **Use anonymized speaker names** and CoLoop labels every speaker with a code instead of a name, so no participant name appears in a transcript's speaker labels, in analysis, or in an export. Names spoken aloud in the conversation are left alone; **PII redaction** handles those. The option is off by default and chosen per transcription, so a file already transcribed keeps its names until you [transcribe it again](#transcribing-again). Anonymization covers audio and video; a transcript you upload as a document keeps the names written in it.
The code comes from the file name, copied exactly as written there. `KTL-3 session.mp4` labels its one participant `KTL-3`; where a file has several, each takes the code plus their own speaker letter, `KTL-3-A` and `KTL-3-B`. Moderators are labelled `Moderator`, or `Moderator 1` and `Moderator 2` when a session has several.
A file name with no code in it leaves CoLoop nothing to build a label from, so those speakers keep the labels transcription gave them, `Speaker A` and `Speaker B`, and you can name them yourself. Name your files consistently before uploading so every one of them carries a code.
### Label speakers
All text within a transcript must be attributed to a speaker.
After transcription, CoLoop will auto-detect and label speakers and their roles.
* **Researcher (Moderators) in blue:** All speech associated with this role will only be used as context, no direct quotes will be cited from moderators as evidence. If there are other voices picked up in the audio ex: video recording, assign this to a Researcher to ensure it will not be used in analysis.
* **Participant in green:** All speech associated with this role will be used in analysis. CoLoop will reference quotes only from participants.
To review or correct a speaker from the **Files** view:
1. Find the file in your project and locate its speakers.
2. Click the role icon to choose **Researcher** or **Participant**.
3. Click the speaker name to open the list of speakers in that file.
4. Select **Confirm name** to keep the current name, or select a different speaker from the list.
5. To rename a speaker in the list, hover over the name and click the edit icon.
6. Enter the new name, then click the **Save** icon or press **Enter**.
Press **Tab** to move between the name field, **Save**, and **Cancel**. Press
**Escape** to cancel the rename.
Confirmed speakers remain editable. You can make the same changes while viewing an individual transcript, where changing the speaker on a turn asks whether to change **This instance only** or the **Whole transcript**. Pick the first for a single mis-attributed turn, the second when the speaker was read wrong throughout.
A change made from the **Files** view or an individual transcript applies only to that file. If the speaker also appears in other files, those labels remain unchanged.
#### Resolve matching speaker names
If the name matches another speaker in the same file, choose how CoLoop should resolve it:
* **Merge** combines both speakers in that file.
* **Keep separate** preserves both speakers and adds a numbered suffix to the edited name.
## Transcribing again
A file that has already been transcribed can be transcribed again with
different options, for example a corrected language or a different speaker
count. Open **Re-do transcription** from the file's row menu.
To re-run several files at once, select them first, then open **Actions** in
the bar at the bottom of the screen (or press ⌘K, Ctrl+K on Windows) and choose
**Re-do transcription**. You pick the options once, confirm the reset, and they
apply to every selected file. Anything in the selection that cannot be
transcribed again is left out and counted in the message that follows: a
document, a file that has never been transcribed or is still transcribing, one
whose media has been deleted, and files with a translator track, which are
re-done from the row menu so their interpreter language can be set per file.
Re-transcribing replaces the transcript, its speakers and their labels.
Anything generated from the old transcript keeps the speaker names it was
built with until it is regenerated.
## Additional features
### Exporting transcripts
Open the download icon next to the file name for **Export options**.
* **Export transcript** downloads a Word document with speaker names and timestamps.
* **Copy transcript** puts the same text on your clipboard.
* **Export summary** downloads the summary, once the transcript has one.
* **Export .srt** downloads subtitles for playing the recording outside CoLoop.
An export contains the language you are viewing. To export a translation, pick it in the language dropdown first; see [Translating transcripts](/docs/setting-up-a-project/translation#read-or-export-a-translation).

To export several files at once, select them in **Files**, open **Actions** at the top of the file list (or press ⌘K, Ctrl+K on Windows) and choose **Export transcripts**. The zip contains every language for every file you selected, each document named with its language code.
### Playing back audio or video
Mouse over the right hand side of the text segment to play back the audio or video.
The scrub bar of the audio or video file is broken down into overarching discussion topics. You can also press any point along the bar to play back the file. Scrolling through the transcript will partially collapse videos to increase visibility of the transcript.

# Fixing speaker names and roles
Source: https://docs.coloop.ai/docs/setting-up-a-project/fixing-speaker-naming
How to rename and re-role speakers across many files at once by describing the naming you want, then reviewing the proposed changes before they are applied.
Speaker labels often arrive in a shape you did not choose: "Speaker 1" across
every file, a moderator named differently in each transcript, or participants
who need the session number in their name. The **Fix speaker names or roles**
action lets you describe the names and roles you want in your own words and
apply them across a selection of files at once.
Nothing is written until you review the proposed changes.
## Renaming a selection
1. In the files view, select the files you want to rename speakers in.
2. Open **Actions** in the bar that appears at the bottom of the screen (or
press ⌘K, Ctrl+K on Windows) and choose **Fix speaker names or roles**.
3. Describe the naming you want, for example "Prefix each participant with the
session number from the file name" or "The moderator is called Sarah in
every file".
4. Choose **Preview changes** and wait for the preview.
5. Review the changes, grouped by file, untick any you do not want, then
choose **Apply**.
File names are part of the context, so instructions can refer to what they
encode: a session number, a date, a market, a respondent.
## Reviewing the proposal
Every speaker in the selection is accounted for:
* **Changed rows** show the old name struck through and the new name beside
it. Role changes are listed too.
* **Unchanged speakers** are collapsed behind a count under each file.
Expand it to see each speaker with a short reason, for example that the
instruction did not say anything about it, or that the name already
matches.
An instruction that only resolves some of your speakers still works. The rest
are left exactly as they are, and you can go **Back** to reword the
instruction and propose again.
## What applying does
Applied changes are confirmed, because reviewing the difference is the check
that confirmation asks for. They apply per file, so a speaker who appears in
several files is renamed only in the files you selected.
Answers, themes, and other outputs generated before the rename keep the old
speaker names until you regenerate them.
## Speakers who appear in several files
A speaker merged across files is decided separately for each one, so an
instruction that reads file names can give that speaker a different name in
each file. Renaming never merges two speakers, and never splits one: each
keeps its own turns.
## When a name is already taken
If a proposed name is already used by another speaker in the same file, both
are kept apart by numbering the later one, `Amelia` and `Amelia (1)`, the same
way [confirming speakers](/docs/setting-up-a-project/confirming-speakers)
does. The same name in two different files is left alone, since those are
separate speakers.
# Language quality
Source: https://docs.coloop.ai/docs/setting-up-a-project/language-quality
What level of transcription and translation quality to expect from CoLoop in each language, and when to budget for researcher review.
Transcription accuracy varies by language. This page tells you what to expect from each one and how much review to budget for. For the full list of languages CoLoop accepts, see [Supported languages](/docs/setting-up-a-project/supported-languages).
## How the pipeline works
CoLoop processes multilingual research in three steps: transcription, then translation, then analysis.
Analysis runs on the original-language transcript, even after you translate a file to English and even when the output you read is in English. Themes and insights come from the source transcript rather than from a translation of it, so nothing drifts in the translation step. Direct participant quotes stay in the language they were spoken in.
Audio quality affects accuracy in every language. Record in a quiet room with a good microphone wherever you can.
## What to expect by language
Ratings describe the transcript CoLoop produces. These are the languages most common in international research programs.
| Language | Transcription | Notes |
| -------------------------- | ------------- | -------------------------------------------- |
| English | 🟢 High | UK, US, and Australian variants |
| French | 🟢 High | Includes Quebecois |
| German | 🟢 High | |
| Spanish | 🟢 High | Multiple dialects |
| Portuguese | 🟢 High | BR and PT variants |
| Italian | 🟢 High | |
| Dutch | 🟢 High | |
| Polish | 🟢 High | |
| Russian | 🟢 High | |
| Turkish | 🟢 High | |
| Swedish, Norwegian, Danish | 🟢 High | |
| Japanese | 🟢 High | |
| Mandarin Chinese | 🟢 High | Simplified |
| Traditional Chinese | 🟢 High | Taiwan, HK, Macau |
| Korean | 🟡 Good | |
| Arabic | 🟡 Good | Modern Standard Arabic; dialects vary |
| Hindi | 🟡 Good | |
| Indonesian, Malay | 🟡 Good | |
| Czech, Slovak, Romanian | 🟡 Good | |
| Thai | 🟡 Good | |
| Vietnamese | 🟡 Good | |
| Hebrew | 🟡 Good | |
| Cantonese | 🟡 Good | Distinct from Mandarin; select it explicitly |
| Urdu | 🟡 Good | |
| Swahili | 🟠 Moderate | |
| Tamil | 🟠 Moderate | |
| Marathi | 🟠 Moderate | |
| Bengali | 🔴 Lower | |
| Gujarati | 🔴 Lower | |
| Burmese, Khmer, Lao | 🔴 Lower | |
Every language CoLoop transcribes can also be translated to English.
## How to plan your project
* 🟢 High: run these end to end without special handling.
* 🟡 Good: have a native speaker check a sample of transcripts before you run full analysis.
* 🟠 Moderate and 🔴 Lower: correct transcripts before you analyze them, and consider human transcription where the audio is poor or the interview is unstructured.
Enter your key words and phrases at the transcription stage, in any language. Brand names, product names, and domain vocabulary are then corrected rather than guessed at.
## Medical and clinical research
Medical Mode adds a correction pass over the terminology general-purpose models most often get wrong: medication names, procedures, conditions, and dosages. It covers English, Spanish, German, and French, and you can combine it with your own key phrases for terminology specific to your study.
Medical Mode is off by default and enabled per account. For clinical research in other languages, standard transcription applies, so enter your key phrases.
## Reading the accuracy bands
The bands above are based on Word Error Rate (WER), the standard measure for transcription accuracy. WER counts the corrections, insertions, and deletions needed to turn an automated transcript into a perfect one, as a percentage of total words.
A high WER does not mean every other word is wrong. Errors cluster around proper nouns, technical terms, strong accents, and fast speech, while the surrounding context stays intact. WER tells you how much researcher review to budget for.
| Band | WER | What it means in practice |
| ----------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🟢 High | Up to 10% | The transcript reads naturally. Occasional errors on proper nouns or specialist terms; you can follow the conversation with minimal review. Key phrases you enter at the transcription stage push the error rate lower still. |
| 🟡 Good | 10% to 25% | Clearly intelligible but imperfect. Some sentences need correction, mostly around names, accents, or domain vocabulary. Budget for a light review pass. |
| 🟠 Moderate | 25% to 50% | Errors are more frequent, concentrated in complex words, fast speech, and strong accents. Meaning is usually recoverable, but review the transcript before you analyze it. |
| 🔴 Lower | Above 50% | Errors are frequent enough that you need to correct the transcript before analysis. Usable, but researcher involvement is significantly higher. |
## How files are routed
CoLoop picks the transcription and translation service that handles each language best. Routing is automatic. Regional dialects such as Quebecois French, Brazilian Portuguese, and Mexican and Argentine Spanish are recognized without a separate setting.
For the list of providers that handle your data, see the [CoLoop subprocessor list](https://trust.coloop.ai/subprocessors).
Cantonese is a distinct spoken language from Mandarin. Select Cantonese, not Chinese, when you set up the file, and review a sample before you analyze it.
## What CoLoop does to limit errors
| Control | What it does |
| ------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Confidence scoring | Words the model was unsure of are highlighted for you to review. The specialist Chinese model and the meeting bot return no per-word confidence, so files transcribed through either show no highlighting |
| Native-language analysis | Transcripts are analyzed in their original language, so meaning does not drift through a translation step |
| Verbatim quotes | Direct participant quotes stay in the language they were spoken in |
| Key phrases | Brand names, product names, and domain terms you supply are corrected rather than guessed at |
| AI correction | A correction pass fixes technical terms, repeated hallucinations, and acronyms, and logs every change it makes |
| Transcript editing | You can review and correct transcripts in any language before analysis begins |
# Adding segments
Source: https://docs.coloop.ai/docs/setting-up-a-project/segments
Learn how to create, import, and manage segments in CoLoop for qualitative research. Build segments for different demographics and markets, and utilize them in the analysis grid and AI chat to filter and analyze data effectively.
If you’re importing data from Recollective or Incling, check out these [articles](/integration/integration/recollective). The segments will be brought in immediately!
Segments allow you to group research participants by customer type, demographic, market or other factors to enable filters and comparisons during analysis. You can apply segments manually, or import an Excel Sheet with screener questionnaire data.
### Manual entry:
1. In the Segments & Participants tab, tick the participants you want. Every speaker in the project is listed, confirmed or not.
2. Click **Add segments** in the bar that appears at the bottom of the screen (it is also under **Actions**, ⌘K, Ctrl+K on Windows).
3. Tick a segment to apply it to everyone selected. A dash means only some of them carry it; ticking again gives it to all.
4. To create a segment, type a name that doesn't exist yet (e.g. "Region: UK", "Age: 18-24"). It is created and applied in one step.
5. If filenames contain metadata (e.g., "Interview\_UK\_Youth"), filter by keyword first to segment everyone matching at once.
The same menu renames participants, sets their role, merges duplicates, and removes every segment from the selection. Each action shows its shortcut, so once you know them you can press the key instead: `S` for segments, `R` to rename, `⇧R` for roles, `M` to merge.
### Merging speakers
A speaker belongs to the file it was found in, so one person interviewed five times is five rows here. Tick the rows and choose **Merge speakers** (`M`) to combine them, then pick which one to keep. A merge cannot be undone, so the dialog says how many turns across how many files will move. Outputs generated before the merge keep the old names until you regenerate them.
When the same confirmed name appears in several files, **Merge duplicates** in the tab's toolbar merges all of them at once. It lists every name that repeats (with the same role), each with the number of speakers and files involved; uncheck any you want to keep apart, then merge. Unconfirmed speakers are left out until you confirm them, and the button only appears while something repeats.
Turn on **Group by file** to read the table the other way round, each file listing the speakers found in it.
### Excel import:
* Upload an Excel sheet containing columns for names and demographic fields.
* CoLoop matches participant names and populates segment data (e.g., gender, location, cohort).

* Ensure names in the Excel sheet **exactly match** those in CoLoop.

* Click **+ Import Files**
* Select the Excel option

* Click 'Process Community Data'
* Click the "Segment" tick box for any columns that correspond to a segment


* Click 'Import community data'
## Using segments
Segment data can be used to filter data when creating grids, chats, and reels. In an [analysis grid](/docs/analysis/analysis-grids) you can also build rows from segments to analyze cross-sections of your data.
* Click **+ Add filter**
* Tick the segment you'd like to apply
* Close the menu to apply them
# Setting up multi-market studies
Source: https://docs.coloop.ai/docs/setting-up-a-project/setting-up-multi-market
This guide covers how to set up multi-market studies, including transcribing and translating multiple languages, and using segments to compare groups.
## Supported languages for transcription and translation
### Which languages are supported for transcription?
CoLoop currently supports over 100 languages with near-human quality (more detail available [here](../setting-up-a-project/supported-languages)).
If you're transcribing online qual files click `detect language` if there are multiple languages present.
### Which languages are supported for translation?
We currently support non-English to English translation of any language. Transcripts do not need to be translated in order to conduct analysis, however quotes and transcripts will be shown in the native language. Always transcribe files in their source language before translating to English.
Ex: A focus group in Spanish must be transcribed first in Spanish, then translate to English.
### What if my language is supported for translation but not transcription?
* Translation within CoLoop can also be applied to txt and docx files.
* If you are working in a language we support for translation but not transcription, you can upload 3rd party transcripts in the native language and translate them in CoLoop.
* Be sure to checkout our formatting guides to ensure your native language transcripts are properly processed (more details [here](/docs/file-formats/docx)).
### Simultaneous translation
Simtrans files are supported by CoLoop in two ways. If you only have the simultaneously translated file, information about who is speaking and their role in the conversation is lost, which can adversely affect analysis. For best results, upload both the original audio/video in tandem with the simtrans file to have CoLoop diarize with more context and decode who is speaking.

From 'Import files,' select Audio or Video (SimTrans), where you'll need both the original and translated video. Once you upload both files, transcribe in the original language and input the number of speakers expected. You won't be able to bulk upload multiple files, but you can bulk transcribe once they are all completed and contain the same number of speakers/language. CoLoop will use the original audio for speaker boundaries/identities, and the translated version will be kept as an additional layer so you can toggle between both languages. All analysis will be conducted using the original language.
If you are conducting Non-English language studies you can also follow the guidelines below:
* Transcribing and analysing in the native language if possible - you'll be able to generate an English translation for any non-English files and will be able to toggle between languages at all times.
* Asking your SimTran service to provide transcripts with labelled speakers
SimTrans files can be uploaded to CoLoop but please consider the following.
1. Theme counts may not be accurate particularly if the interview involved more than 2 speakers
2. CoLoop will not be able to as accurately distinguish moderator and participant statements so you will see moderator highlighted in the evidence panel
3. These can be effectively used for simple use cases like summaries and finding quotes
## Setting up a multi-market project
### **Create a new project**:
* Start by clicking "create project" and give it an appropriate name (e.g., "multi market stack study").
**Upload the Discussion Guide**:
* Upload a single Word document as your discussion guide.
* If using the same guide in different languages, upload only the English version.
* If guides differ by market, compile them into one document and clearly indicate which guide corresponds to each group.
### Uploading, transcribing and translating files
**Audio & Video Files**:
* Upload audio files for each market or language group (e.g., Spanish interviews and English focus groups).
* Use the transcription feature to transcribe files based on their source language.
* For bulk transcription, ensure all selected files share the same source language and number of speakers.
**Transcripts:**
* Upload your transcripts, making sure to follow the formatting guidelines [here](/docs/file-formats/docx).
**Translate Transcripts**:
* Translate non-English transcripts into English using the translation feature.
* 'Bulk Transcribe' the files in one go, by selecting your files and then choosing 'Translate' from the Actions menu that appears.
* Note that translations can only go from a original language into English.
**Community Data:**
* Please select 'Auto-Detect' as the transcription option for Community data files with multiple languages. (Please note this only works for community data from platforms CoLoop is integrated with - list [here](/docs/file-formats/community-data)).
* Users can translate community data files by either selecting the file in the Files view and choosing 'Translate' from the Actions menu, or by opening the community data file and clicking the three dots at the top and selecting 'translate activity'.
### Set up segments
**Add Market Segments**:
* Label participants with segment tags corresponding to their market or region (e.g., "Spanish" for Spanish participants, "English" for English participants).
* Bulk-apply these segments by selecting multiple participants and editing their labels.
* More information on setting up segments [here](/docs/setting-up-a-project/segments).
**Leverage Segments in Analysis**:
* Use custom grids to create separate rows for each market segment (e.g., English group vs. Spanish group).
* Generate questions based on your discussion guide and obtain summaries for each segment.
* Utilize chat features to compare experiences or responses between different market segments.
# Supported languages
Source: https://docs.coloop.ai/docs/setting-up-a-project/supported-languages
This document provides an overview of the languages supported by CoLoop for transcription and translation.
CoLoop is designed to support transcription and translation in over 100 languages, enabling researchers, teams, and organizations to work with diverse data effortlessly.
CoLoop supports UK, US, and Australian English, allowing users to choose the variant that best matches their needs. In addition to these specific variants, our English (Global) model is designed to recognize and accurately transcribe a wide range of English accents, ensuring high-quality results regardless of regional pronunciation or speaker background.
The transcription dialog shows the languages available for your account. If a
language does not appear, select a different language or contact CoLoop
support.
| Languages | | |
| --------------------- | -------------- | -------------------- |
| Afrikaans | Albanian | Amharic |
| Arabic | Armenian | Assamese |
| Azerbaijani | Bashkir | Basque |
| Belarusian | Bengali | Bosnian |
| Breton | Bulgarian | Cantonese |
| Catalan | Chinese | Chinese (Simplified) |
| Chinese (Traditional) | Croatian | Czech |
| Danish | Dutch | English |
| Esperanto | Estonian | Faroese |
| Finnish | French | Galician |
| Georgian | German | Greek |
| Gujarati | Haitian Creole | Hausa |
| Hawaiian | Hebrew | Hindi |
| Hungarian | Icelandic | Indonesian |
| Interlingua | Irish | Italian |
| Japanese | Javanese | Kazakh |
| Kannada | Korean | Latin |
| Luxembourgish | Lingala | Lao |
| Lithuanian | Latvian | Malagasy |
| Māori | Macedonian | Malayalam |
| Mongolian | Marathi | Malay |
| Maltese | Nepali | Norwegian |
| Occitan | Punjabi | Polish |
| Pashto | Persian | Portuguese |
| Romanian | Russian | Sanskrit |
| Sindhi | Sinhala | Slovak |
| Slovenian | Shona | Somali |
| Serbian | Sundanese | Swedish |
| Swahili | Tamil | Telugu |
| Tajik | Thai | Turkmen |
| Filipino | Turkish | Tatar |
| Uyghur | Ukrainian | Urdu |
| Uzbek | Vietnamese | Yiddish |
| Yoruba | | |
For the level of accuracy to expect from each language, see [Language quality](/docs/setting-up-a-project/language-quality).
# Translating transcripts
Source: https://docs.coloop.ai/docs/setting-up-a-project/translation
Learn how to transcribe your files from a non-English language in CoLoop.
CoLoop offers translation options for over 100 languages in order to facilitate analysis. See a full list of languages [here](/docs/setting-up-a-project/supported-languages).
### In all files
Upload all your files and transcribe in the source language. Tick the files you want (or select all), then open **Actions** in the bar that appears at the bottom of the screen (or press ⌘K, Ctrl+K on Windows) and choose **Translate**. CoLoop will automatically translate every selected file into English.

### In an individual transcript
* In order to translate your transcript into English, click on the three dots next to the file name when the transcript is open and then 'Translate transcript'
* Clicking the reset button will undo all translation, speaker labelling and annotations.

### Read or export a translation
Translating always keeps the original transcript available, as well as the English version.
Switch between them with the language dropdown next to the file name; the source language is marked **Original**.
An export contains the language you are viewing, so pick it before exporting. See [Exporting transcripts](/docs/setting-up-a-project/create-a-transcript#exporting-transcripts), including how to download both languages at once.
### Analysis language
CoLoop answers in the language of your question. It analyzes the original-language transcript rather than the translation, and participant quotes stay in the language they were spoken in. See [Language quality](/docs/setting-up-a-project/language-quality) for what to expect from each language.
# Ask the Community
Source: https://docs.coloop.ai/docs/troubleshooting/ask-the-community
The CoLoop Community is a dedicated space for researchers to troubleshoot issues, share insights, collaborate, and stay updated on AI-powered research.
### CoLoop Community
Need help troubleshooting your AI Copilot? Join the **CoLoop Community**, a dedicated space where researchers can connect, collaborate, and get expert support. Share insights, exchange tips, and stay updated on AI-powered research trends. Whether you need troubleshooting help or guidance on making the most of CoLoop, this community is here to support you.
🔗 **Join here:** [CoLoop Community](https://community.coloop.ai/users/sign_in)
You can use your CoLoop login to sign in. If you don't have a CoLoop login, you can sign up by clicking on "CoLoop login" and then selecting "Sign Up".
# Contact Support
Source: https://docs.coloop.ai/docs/troubleshooting/contact-support
### Support Hours
Our support team is available from 9:00 am through 5:00 pm UK hours, with the exclusion of UK National Holidays. We will aim to get back to you as soon as we can.
### How to Contact Support
You can initiate a helpdesk ticket during Support Hours at any time by emailing [support@coloop.ai](mailto:support@coloop.ai) or via Slack.
# FAQs
Source: https://docs.coloop.ai/docs/troubleshooting/faqs
This document will take you through answers to frequently asked questions.
**What kind of data can I upload into CoLoop?**
* CoLoop can process a range of unstructured qualitative data including audio and video recordings (with transcription available in 100+ languages), pre-existing transcripts, open-ended survey responses, exports from community platforms, and concept or stimulus decks. The platform is designed to support primary qualitative research and works best with data that can be attributed to individual speakers or participants.
**What languages does CoLoop support?**
* CoLoop supports over 100+ languages for transcription and translation. Find the full list [here](/docs/setting-up-a-project/supported-languages).
**Can CoLoop help me write my research reports?**
* CoLoop helps researchers analyze qualitative data by automatically surfacing patterns, themes, and sentiment across transcripts, recordings, and open-ended responses. It links insights directly to source material for easy verification and allows users to organize findings in customizable analysis grids. For reporting, CoLoop makes it easy to extract key quotes, create video and audio clips, and export toplines or structured outputs that can be directly used in presentations and reports.
**Can CoLoop summarise documents, slide decks or pdfs?**
* No — CoLoop is designed specifically for primary qualitative analysis. It works best with rich, spoken content like interviews, focus groups, or community discussions where speaker identity and context are clear. Since CoLoop relies on linking insights back to individual speakers and moments in the conversation, it’s not built to analyse static files like documents, slide decks, or PDFs.
**How can I describe CoLoop to my clients?**
* CoLoop is an AI-powered analysis tool designed to streamline qualitative research by efficiently processing interviews, focus group data, and open-ended survey responses. It enables researchers to transcribe recordings, create customizable analysis grids, generate thematic codebooks, perform sentiment analysis, thereby accelerating the extraction of key insights from unstructured data.
**Is CoLoop accessible?**
* Accessibility is a key consideration at CoLoop. Current features include accessible tab navigation, multiple screen contrast options, and a colour palette designed to be readable for users with colour blindness. Unfortunately, we do not offer screen reader functionality at the moment.
# Box
Source: https://docs.coloop.ai/integration/integration/box
Import audio and video files from Box into a CoLoop project.
If your interview recordings live in Box, you can import them into a CoLoop project directly. There is no need to download files to your computer and upload them again. Connect your Box account once, then browse or search your Box from inside CoLoop and import files in bulk.
The Box integration is being rolled out gradually and may not be visible in your account yet. [Contact support](mailto:support@coloop.ai) to request access.
## Connect your Box account
You connect Box once and the connection works in all your projects. Each person connects their own Box account, so CoLoop sees exactly the files that account can see in Box. No admin setup is required.
1. Inside a project, click **Import Files** and select **Box**.
2. Click **Connect Box**.
3. Sign in to Box and approve the request.
Box then returns you to CoLoop, ready to import.
Box's approval screen asks for permission to read and write your files. CoLoop only downloads the files you choose to import and never changes or deletes anything in your Box account. Box requires this permission level to allow downloads.
## Import files
1. Click **Import Files** and select **Box**.
2. Find your files:
* Browse folders starting from **All Files**. Use the breadcrumbs at the top to move back up.
* Or search your whole Box with the search field. Type at least two characters. Search results show where each file lives.
3. Tick the files you want. Only audio and video files have checkboxes; other file types cannot be imported from Box. Your selection is kept as you move between folders and searches.
4. Review your selection with the file count and total size shown at the bottom left. Click it to see the full list, remove individual files, or **Clear all**.
5. Click **Import**. If you selected more than 50 files, CoLoop shows the total size and asks you to confirm before starting.
CoLoop confirms the import started and closes the window. Files download from Box in the background and appear in your project as they arrive, and transcription starts automatically. You can keep working while this happens.
Useful to know:
* You can import up to 1,000 files at a time.
* Importing the same Box file into the same project again does not create a duplicate. CoLoop keeps the copy it already has.
* See [Video & Audio](/docs/file-formats/video-audio) for the supported formats.
## Manage your connection
Your Box account name appears at the top right of the import window. Click it to:
* **Reconnect**: sign in to Box and approve the connection again.
* **Disconnect**: remove CoLoop's access to your Box account. Files you have already imported stay in your projects; they are copies stored in CoLoop.
If you don't use the connection for around 60 days, Box expires it. CoLoop then shows "Your Box connection can no longer be refreshed" and asks you to reconnect. Click **Connect Box** and sign in again to carry on.
## Troubleshooting
* **You don't see the Box option in Import Files.** The integration isn't enabled for your account yet. [Contact support](mailto:support@coloop.ai) to request access.
* **"Nothing imported. No media files were selected."** Your selection contained no audio or video files. Select at least one recording and try again.
* **"Couldn't load your Box connection."** This is usually temporary. Click **Try again**.
* **A file you expect is missing from the browser.** CoLoop shows what your Box account can access. Check that the file is visible when you sign in to Box directly, or ask its owner to share it with you.
## Recommended Articles
This article explains best practices, language support as well as tips and tricks for getting the most out of CoLoop's transcription
This article provides additional details on working with Audio & Video files within CoLoop including supported formats and best practices
# Discuss IO
Source: https://docs.coloop.ai/integration/integration/discuss
Learn how to upload interview transcripts and videos from Discuss IO to CoLoop for analysis. Follow these steps to export your data from Discuss IO and seamlessly integrate it into CoLoop for transcription, content analysis, and more.
You can upload interview transcripts and videos from Discuss IO for analysis in CoLoop.
## Exporting data from Discuss IO
First you will need to download audio or video files from your sessions by going to the ‘Recordings‘ tab on your project in Discuss IO.
Once you are on the recordings page, select the video you wish to download the audio from. Navigate to the "Tools & Downloads" button on the right.
From the dropdown menu choose either ...
* **Original Video (.mp4)**: this is recommended if you are planning to use CoLoop to create video clips
* **Original Audio (.mp3)**: this is recommended if you are planning to use CoLoop for content analysis only. These files are smaller and will upload better.
* **Original Transcript (.doc)**: this is recommended if you have human written transcripts of your interviews
## Uploading the files to CoLoop
Once you have downloaded your files from Discuss simply upload them to CoLoop using the corresponding option below (docx; video or audio)
# Uploading Discuss IO formatted DOCX files
* Transcripts from Discuss IO contain timestamps.
* These need to be reformatted to work in CoLoop
* The tool below will considerably speed up this process
* Upload the docx file to the modal below
* Click 'Download as Text File' to get the result
* All file conversion occurs **locally** so the docx file **never leaves your machine**
***
## Converting files to CoLoop format
We are currently working on adding native support to CoLoop for Discuss IO transcripts
* Upload DOCX files in Discuss IO format to the tool below.
* These files are converted securely and locally to a CoLoop supported format
# Dscout
Source: https://docs.coloop.ai/integration/integration/dscout
Discover how to leverage CoLoop for analyzing Dscout projects. Export entry data and media from Dscout missions, import it into CoLoop, and optimize your analysis workflow.
CoLoop supports the analysis of Dscout Diary, Express, and Usability Test missions, including text-based entry data as well as photo and video media.
## Exporting Data from Dscout
#### 1. **Export Entry Data (csv)**
To export entry data from a Dscout mission for import into CoLoop:
1. Open your mission in Dscout
2. Navigate to the **Entries** page (Diary) or **Responses** tab (Express/ Usability Test)
3. Click the **export icon** in the top-right corner of the screen (a box with an arrow pointing out of it)
4. In the export menu, go to the **Basic** tab
5. Click **Entry data** to download a `.csv` file of all participant responses, including transcripts of any video responses
**Note:** Exports may take some time depending on the volume of data in your mission.
#### 2. Export Media (Photos & Videos)
To export photo and video data from a Dscout mission for import into CoLoop:
1. Open your mission in scout
2. Navigate to the **Entries** page (Diary) or **Responses** tab (Express/ Usability Test)
3. Click the **export icon** in the top-right corner of the screen
4. In the export menu, go to the **Basic** tab
5. Click **Photos and videos** to download a `.zip` archive of all media files submitted by participants
## Importing Dscout data into CoLoop
To import Dscout data into CoLoop:
1. Click **Add Files**
2. Select **Dscout**
3. Follow the on-screen instructions to upload your files: First, upload the **(1) Entry data CSV** file, then upload the **(2) Media ZIP** file (if applicable)
**Important:** You must always upload the Entry data CSV file. Media ZIP files cannot be uploaded without the accompanying CSV. It is best to upload them together at the same time.
## Viewing Dscout data in CoLoop
Once your Dscout data has uploaded into CoLoop, you can click to view the data inside.

CoLoop will look at all data by default. To receive more granular analysis, try searching via filter or segment.
# Field Notes
Source: https://docs.coloop.ai/integration/integration/field-notes
Learn how to seamlessly integrate entire projects from Field Notes into CoLoop for analysis. Follow these steps to export data from Field Notes in a CoLoop optimized JSON format, upload it to CoLoop, and utilize the briefing document to provide context for enhanced AI analysis.
You can upload entire projects from [Field Notes](https://www.fieldnotes.space/) into CoLoop for analysis using the Field Notes and CoLoop integration.
## Exporting data from Field Notes
Downloaded JSON files contain links that are valid for 8 hours only! Make sure to upload these to CoLoop straight after downloading them.
First you will need to download a CoLoop optimised export format from your Field Notes account. This will generate a JSON file that can be uploaded to CoLoop.
1. Click on the Downloads tab
2. Then click “New download”
3. and finally “Download for CoLoop.ai”
## Uploading to CoLoop
The briefing document in the project setup helps CoLoop understand the background context to your research. We strongly recommend providing one to make sure the AI understand the context and objectives of your research!
Once you have downloaded your files from Field Notes simply upload them to CoLoop using the corresponding Field Notes option.
1. [Create a project in CoLoop](/docs/setting-up-a-project/create-a-project)
2. Upload your briefing document, as a reminder this should:
1. Contain an overview of your research project
2. Include the key objectives
3. Be in DOCX format
3. Use the Field Notes option to import the json file
## Finishing Up
Once you’ve uploaded your research project CoLoop will index them into memory for you to start your analysis! We recommend checking out our guides & best practices for analysing online qual projects here.
# Google Meet
Source: https://docs.coloop.ai/integration/integration/google-meet
Learn how to add CoLoop to a Google Meets meeting, record interviews, and upload to a project instantly.
CoLoop can be integrated directly with Google Meet to capture and record interviews live as they are conducted. The recordings will be kept within the project you've selected and take away the layer of uploading videos to CoLoop. This can help to streamline the operational process and improves speaker accuracy particularly when conducting focus groups with multiple participants.
## **CoLoop Recorder Key Information for Google Meet**
**Supported Features**
* Full support for standard google meet meetings.
* Scheduling in advance supported.
**Limitations**
* Google Meet Livestreams are not supported.
* Breakout rooms are not supported.
## How to Use CoLoop Recorder with Google Meet
### **Create a project in CoLoop**
1. Open the project you're recording an interview for within CoLoop ([Creating a project](/docs/setting-up-a-project/create-a-project) for more information.)
### Invite the Recording Bot using one of Two Methods
**+Join Meetings**
You can have CoLoop join meetings ad-hoc or right before meetings start by entering in the meeting URL after clicking 'Join meeting.'
2. Click on the '+' sign next to the Meetings tab on the left hand menu.
3. In the Google Meets calendar invite copy the meeting link and paste the invite into the URL box.
4. Enter a name for the meeting to name the file once it's uploaded.
5. Select now for the CoLoop Recorder bot to join immediately or select later and enter in the time. CoLoop recorder will wait in the waiting room for 10 minutes once the call starts.
**Project Specific Email Invite**
Create an email address for specific CoLoop projects and add that email to all associated calls.
This method is ideal for adding CoLoop to multiple meetings or for allowing third parties to schedule calls by using the project-specific email.
1. Navigate to the **Meetings** section in CoLoop.
2. Select **Email Invite** and create an email address for the project.
### Allow the recording bot into the call
* At this point we recommend ensuring you have obtained permission to record from your participants
* Allow the meeting bot to record the meeting.
* The **CoLoop Recorder** will start recording soon thereafter.
### Viewing Recordings
* After you have finished the meeting, CoLoop will automatically import the meeting recording.
* To view the meeting recording, navigate to **Files** tab in your project.
* From here simply follow the steps to transcribe your file ([Creating a transcript](/docs/setting-up-a-project/create-a-transcript))
### **Managing Meeting Bot Settings**
Meeting bot settings can be managed on an organisation level, or on a project level.
Video Output:
* In meetings by default, CoLoop will appear on the screen as another participant. To turn this off please toggle it off under 'Video Output'.
**Organisation Level:**
Making changes at an organisational level will make those changes effective across every single project.
**Project Level Management:**
Making changes at the project levels will affect all call recordigns associated with that project only.
# incling
Source: https://docs.coloop.ai/integration/integration/incling
Learn how to easily export your data from incling and upload it to CoLoop. Our step-by-step guide covers exporting data, supported activities, and uploading files, ensuring a seamless transition for your projects.
### Uploading incling Projects
You can directly export your data from incling and upload it straight to CoLoop. Types of data compatible with CoLoop are:
* All screener data
* All participant data (active and retired)
* All task data, including participant answers, slider and ranking responses, and replies
* Images, audio, and video attached to task answers, including captions and transcripts when available
CoLoop accepts current and earlier incling export formats. Keep the ZIP or JSON file unchanged and upload it within 24 hours of downloading it.
Please note that CoLoop is not able to support other activities such as live chats and tasks which involve visually tagging images.
## Exporting data from incling step-by-step
Please note that your downloaded incling file contains temporary URLs for securely transferring media directly from incling to CoLoop. As such, files will expire 24 hours after download.
Click on the three bars in the top right hand corner and select import/export.

Select 'Create CoLoop Export'.

Scroll to the bottom of this page, and click export.

You will then be redirected to the 'Retrieve' page and the export will take a couple of minutes to process. When it's ready a 'Download' button will appear and then your file is ready to download.

Once you press 'Download', your incling data will be saved as a ZIP file in your device's downloads folder. This ZIP file contains a JSON file with all your incling data. You can upload either the ZIP file, or the JSON to CoLoop.
## Uploading the files to CoLoop
Upload your incling file (ZIP or JSON) to CoLoop using the incling import button. Make sure you the file you upload is unedited. Also make sure that the file was downloaded less than 24 hours ago, otherwise the links inside will have expired and the file will not upload.
Your file will then be ready to process.

Provide the tool with relevant information and then begin transcription. If you have multiple languages please select 'auto-detect'. This may take a couple of minutes.
After transcription, CoLoop will have automatically assigned all relevant segments to participants and you will be ready to begin analysis.
# Listen Labs
Source: https://docs.coloop.ai/integration/integration/listen-labs
Import Listen Labs survey data into CoLoop for qualitative analysis using AI-powered grids and chat.
Import your Listen Labs survey responses into CoLoop to analyze open-ended feedback with AI-powered grids and chat.
## Exporting Data from Listen Labs
To export your data from Listen Labs:
1. Open your project in Listen Labs
2. Click **Export complete responses**
3. Download the Excel file to your computer
## Importing into CoLoop
To import your Listen Labs data:
1. Open your project in CoLoop and click **Add Files**
2. Scroll to the **Integrations** section
3. Click **Listen Labs**
4. Select your exported Excel file
CoLoop will process your file and index the responses for analysis.
## Analyzing Your Data
Once your data is imported, you can analyze it using:
* **Grids** for structured thematic analysis across questions
* **Chat** for flexible, conversational exploration of your data
By default, CoLoop analyzes across all your data. To focus on specific questions:
1. In the chat input area, click **Add filter**
2. In the Data Filters dialog, click **Add files filter**
3. Select your Listen Labs file to expand it
4. Expand activities to see individual questions
5. Check the specific questions you want to analyze
Filtering by question helps you get more focused insights rather than analyzing the entire dataset at once.
For more on analysis techniques, see [Analysis Grids](/docs/analysis/analysis-grids) and [Chat 2.0](/docs/analysis/chat-2.0).
# One Drive
Source: https://docs.coloop.ai/integration/integration/one-drive
Large audio and video files can be imported directly into CoLoop for analysis from One Drive. One Drive is typically used by independent 3rd party moderators working out of personal accounts for sharing large files. This integration can be used to import large video or audio files directly into CoLoop.
## Importing a file
MS OneDrive currently has a bug a which means users need to order / reorder the list of files for them to show up when opening this for the first time
* Click Import Files inside a CoLoop project
* Click the OneDrive button in the upload modal
* Follow the instructions to sign in securely to One Drive
* Choose the file(s) you want to import and press select
## Recommended Articles
This article outlines a quick start guide and some best practices for analysing Live Interviews in CoLoop
This article explains best practices, language support as well as tips and tricks for getting the most out of CoLoop's transcription
This article provides additional details on working with Audio & Video files within CoLoop including supported formats and best practices
# Qualzy
Source: https://docs.coloop.ai/integration/integration/qualzy
Learn how to seamlessly integrate entire projects from Qualzy into CoLoop for analysis. Export data from Qualzy in a CoLoop optimized Excel format, upload it to CoLoop, and utilize the briefing document to enhance AI analysis with contextual information and project objectives.
You can upload entire projects from [Qualzy](https://qualzy.com/) into CoLoop for analysis using the Qualzy and CoLoop integration.
## Exporting data from Qualzy
Downloaded Excel files contain links that are valid for 12 hours only! Make sure to upload these to CoLoop straight after downloading them.
First you will need to download a CoLoop optimised export format from your Qualzy account. This will generate a Excel file that can be uploaded to CoLoop.
1. Click on the Responses tab
2. Then click the Excel Icon
3. Set the export options as shown below (Include expirable links; Tiny quality image files, Leave the "limit the tags" section empty)
4. Click on the "Reports & Exports" section
5. Download the file



## Exporting data from the response window
Users can also export data from the Qualzy responses window. Click on the export button on the top left of the screen and select the "CoLoop.ai Data File" export button.

Then users just needs to choose export from the confirmation window.

The excel transcript will be exported straight into file explorer.
## Uploading to CoLoop
The briefing document in the project setup helps CoLoop understand the background context to your research. We strongly recommend providing one to make sure the AI understand the context and objectives of your research!
Once you have downloaded your XLSX file from Qualzy simply upload it to CoLoop using the corresponding Qualzy option.
1. [Create a project in CoLoop](/docs/setting-up-a-project/create-a-project)
2. Upload your briefing document, as a reminder this should:
1. Contain an overview of your research project
2. Include the key objectives
3. Be in DOCX format
3. Use the Qualzy option to import the xlsx file

## Finishing Up
Once you’ve uploaded your research project CoLoop will index them into memory for you to start your analysis!
# Recollective
Source: https://docs.coloop.ai/integration/integration/recollective
Discover how to leverage CoLoop for analyzing Recollective projects. Export text, video, and photo data from Recollective, import it into CoLoop, and optimize your analysis workflow. Ensure compliance with privacy standards by excluding unnecessary participant photos and emails from exports
CoLoop supports the analysis of Recollective Projects. This is currently limited to text based tasks with support for image, video and audio available from Q4 2024.
## Exporting Data From Recollective
Read Recollective's full guide on exporting data [here](https://helpdesk.recollective.com/article/62-overview-of-transcripts-and-data-exports)
### 1. Export Activity Data
To export xlsx text data from Recollective for import into CoLoop:
1. Open the project in Recollective
2. Click on the Admin tab
3. Click Activities and select the following options below (minimum)
4. Click generate transcript
* Formatted Spreadsheet (EXCEL)
* Instructions and responses
* Comments
* All Participant
\*we recommend unchecking '**Include participant photos**' and '**Include participant emails**' these output do not contribute to the analysis and will generate unnecessary PII.

### 2. Export Video Data
To export video data from Recollective for import into CoLoop:
1. Open the project in Recollective
2. Click on the Admin tab
3. Click Videos
4. Click "Generate Archive"


### 3. Export Photo Data
To export photo data from Recollective for import into CoLoop:
1. Open the project in Recollective
2. Click on the Admin tab
3. Click Photos
4. Click "Generate Archive"

### 4. Export File Data
If your project uses file upload tasks, export their files the same way:
1. Open the project in Recollective
2. Click on the Admin tab
3. Click Files
4. Click "Generate Archive"
Only image, video, and audio files from file upload tasks are imported into
CoLoop. Other file types (such as PDF, DOCX, or PPTX) are skipped during
import and won't appear in the analysis.
## Importing Recollective Data Into CoLoop
To import Recollective data...
1. Click add files
2. Click Recollective
3. Follow the instructions to upload (1) xlsx files, then the (2) video, image, and file archive zip files

Please note, you must always upload the excel file. Video, Image, or File archive zips won't upload without the accompanying excel. It's best to upload them all at once.
## Viewing your Recollective Files & Segments
Once you Recollective data has uploaded into CoLoop, you can click open to view the data inside.

You can toggle between activities by clicking on the drop down at the top of the screen, once you've opened the file.

Recollective imports will also automatically carry across all of the segment information:

# SharePoint
Source: https://docs.coloop.ai/integration/integration/share-point
Import files and whole projects from SharePoint into CoLoop.
You can import large audio and video files directly from SharePoint into CoLoop for analysis. An organization admin connects your SharePoint site once, then everyone in the organization can import files from it.
## Setting up the connection
You must be an organization admin to set or change the SharePoint URL for an organization workspace. If you use a personal workspace, you can configure the URL yourself.
1. Inside a CoLoop project, click **Import Files**.
2. Move your pointer over **SharePoint**, then click the settings icon.
3. Paste the full URL of your SharePoint site, including any site path. For example: `https://contoso.sharepoint.com/sites/research`.
4. Click **Submit**.
The URL must use HTTPS and belong to SharePoint Online. CoLoop supports sites hosted on `sharepoint.com`, `sharepoint.us`, and `sharepoint.cn`. Do not include a custom port, query parameters, or a URL fragment.
If you are not an organization admin and SharePoint has not been configured, ask an admin to complete these steps. After setup, organization members can import files without changing the shared URL.
## Importing a file
* Click on the SharePoint option in the Import files window
* Follow the steps to securely sign into your Microsoft account
* Choose file(s) from the list shown and click `Select`
* CoLoop will rapidly upload multiple files
* From here you can transcribe, process, and analyze your files
## Importing whole projects from a folder
This feature is being rolled out gradually and may not be enabled for your account yet. [Contact support](mailto:support@coloop.ai) to request access.
If your research is already organized into folders in SharePoint, you can create many projects at once instead of importing files one project at a time.
1. From your CoLoop home space, click **Import Projects** next to **Create**.
2. Connect your Microsoft account if you haven't already, then paste your SharePoint site URL.
3. Select the folders you want to import. Each selected folder becomes its own project, named after the folder.
4. Review the preview. CoLoop shows the transcript count and discussion guide it will use for each project.
5. Deselect any folders you don't want, then confirm.
For each selected folder, CoLoop creates a project and imports its contents:
* A `.docx` file is used as the project's **discussion guide**. If a folder contains more than one `.docx`, CoLoop suggests the most likely guide (preferring files in a folder named `Discussion Guide`); you can pick a different one, or no guide, from the dropdown in the preview.
* All `.txt`, audio, and video files (including those in nested subfolders) are imported as **transcript resources**.
* `.docx` files inside a folder named `Transcripts` are imported as transcripts rather than treated as guide candidates. The folder name must match exactly, including capitalization.
* When the same recording exists as both an audio and a video file (same name, same folder), only the video is imported.
You can import up to 30 folders at a time. To import more, run the import again — folders you've already imported are marked in the preview and are skipped on re-import, so running the import again won't create duplicates.
Large imports run in the background, so you can keep working while projects are created.
## Recommended Articles
This article outlines a quick start guide and some best practices for analyzing Live Interviews in CoLoop
This article explains best practices, language support as well as tips and tricks for getting the most out of CoLoop's transcription
This article provides additional details on working with Audio & Video files within CoLoop including supported formats and best practices
# Teams
Source: https://docs.coloop.ai/integration/integration/teams
Learn how to integrate your Microsoft Outlook calendar with CoLoop, allowing you to schedule in advance and automatically upload and record in CoLoop.
CoLoop can be integrated directly with Teams to capture and record interviews live as they are conducted. This can help to streamline research ops and will also significantly improve speaker accuracy particularly when conducting focus groups with multiple participants.
## **CoLoop Recorder Key Information for Teams**
**Supported Features**
* Full support for standard Microsoft Teams meetings.
* Scheduling in advance supported.
**Limitations**
* Non-standard Teams meeting types are not supported, including:
* Registration-required meetings & webinars
* Teams Live Events
* Town Hall Events
* Direct one-to-one calls
* Microsoft 365 GCC High Cloud meetings
* Any meeting or webinar requiring attendee registration is not supported.
* Breakout rooms are not supported.
* If you set a custom bot name in meeting bot settings, it applies to Zoom and
Google Meet. In Teams, the bot still appears as CoLoop Recorder.
## How to Use CoLoop Recorder with Teams
You can record Teams meetings in CoLoop in two ways. You must have a project to upload the recordings into and all calendar invites must have a Teams link for the recorder bot to join.
### **Create a project in CoLoop**
1. Open the project you're recording an interview for within CoLoop ([Creating a project](/docs/setting-up-a-project/create-a-project) for more information.)
### Invite the Recording Bot using one of Two Methods
**+Join Meetings**
You can have CoLoop join meetings ad-hoc or right before meetings start by entering in the meeting URL after clicking 'Join meeting.'
2. Click on the '+' sign next to the Meetings tab on the left hand menu.
3. In the Teams app, copy the meeting link and paste the invite into the URL box.
4. Enter a name for the meeting to name the file once it's uploaded.
5. Select now for the CoLoop Recorder bot to join immediately or select later and enter in the time. CoLoop recorder will wait in the waiting room for 10 minutes once the call starts.
**Project Specific Email Invite**
Create an email address for specific CoLoop projects and add that email to all associated calls.
This method is ideal for adding CoLoop to multiple meetings or for allowing third parties to schedule calls by using the project-specific email.
1. Navigate to the **Meetings** section in CoLoop.
2. Select **Email Invite** and create an email address for the project.
### Allow the recording bot into the call
* At this point we recommend ensuring you have obtained permission to record from your participants
* Allow the meeting bot to record the meeting.
* The **CoLoop Recorder** will start recording soon thereafter.
### Viewing Recordings
* After you have finished the meeting, CoLoop will automatically import the meeting recording.
* To view the meeting recording, navigate to **Files** tab in your project.
* From here simply follow the steps to transcribe your file ([Creating a transcript](/docs/setting-up-a-project/create-a-transcript))
### **Managing Meeting Bot Settings**
Meeting bot settings can be managed on an organisation level, or on a project level.
Video Output:
* In meetings by default, CoLoop will appear on the screen as another participant. To turn this off please toggle it off under 'Video Output'.
**Organisation Level:**
Making changes at an organisational level will make those changes effective across every single project.
**Project Level Management:**
Making changes at the project levels will affect all call recordigns associated with that project only.
# Tellet
Source: https://docs.coloop.ai/integration/integration/tellet
Connect Tellet to CoLoop so you can send completed Tellet interview transcripts into a CoLoop project for analysis.
Connect Tellet to CoLoop to send completed interview transcripts from a Tellet project into a CoLoop project. After setup, each pushed transcript appears in CoLoop for coding, tagging, grids, and chat.
## Requirements
Before you start, make sure you have:
* A CoLoop account with access to the workspace and project you want to send transcripts to
* Organization Owner or Admin access in Tellet to connect or disconnect CoLoop
* A Tellet project with at least one completed conversation to send
After an admin connects CoLoop, any Tellet member can send eligible transcripts from linked Tellet projects.
## Connect CoLoop in Tellet
Connect CoLoop once for each Tellet organization.
1. In Tellet, open the organization menu next to your organization name.
2. Click **Integrations**.
3. On the CoLoop card, click **Connect to CoLoop**.
4. Sign in to CoLoop and approve the requested access.
5. Return to Tellet and confirm that the CoLoop card shows **Connected**.
Tellet sends transcripts through the CoLoop account used during setup. Tellet shows this person under the connection status so admins can see which CoLoop account owns the connection.
If the login used to connect CoLoop loses CoLoop access or leaves your organization, Tellet cannot send transcripts until an admin reconnects.
To transfer the connection later, click **Reconnect to CoLoop** in Tellet and sign in with the new CoLoop account. Tellet uses that account for future pushes.
## Link a Tellet project to a CoLoop project
Link each Tellet project to the CoLoop project that should receive its transcripts.
1. In Tellet, open the project you want to send.
2. Go to the **Results** page.
3. Click **Send to CoLoop** (top right, next to Download Analysis).
4. Choose the CoLoop workspace for the project.
5. Choose the CoLoop project where the transcripts should appear.
6. The link is saved. You can now send transcripts.
You can link multiple Tellet projects to the same CoLoop project when they belong in the same analysis workspace. For example, link several waves of the same study to one CoLoop project if you want them to share a codebook.
To change the destination, click **Unlink** in Tellet and choose a new CoLoop project.
## Send transcripts to CoLoop
After a Tellet project is linked, you can send its completed transcripts.
1. In Tellet, open the project's **Results** page.
2. Click **Send to CoLoop**.
3. Click **Push all conversations to CoLoop**.
Tellet uploads every eligible transcript in the project. Progress appears in the Tellet panel while the push runs.
| Status | Meaning |
| --------- | ------------------------------------------------------------------------------------- |
| Pending | The transcript is queued and waiting to be sent. |
| In flight | The transcript is uploading to CoLoop. |
| Succeeded | The transcript is available in CoLoop. |
| Failed | Tellet could not send the transcript. Hover over the row in Tellet to see the reason. |
| Skipped | The conversation is not eligible to send. |
You can push the same Tellet project again. Transcripts already in CoLoop are updated in place, so repeated pushes do not create duplicates.
## Which conversations are sent
Tellet sends:
* Fully completed interviews
* Interviews that Tellet has already processed for analysis
Tellet does not send:
* Interviews still in progress
* Abandoned or incomplete interviews
* Test conversations and sandbox previews
* Prescreened-out participants
* Deleted conversations
## What Tellet sends
For each conversation, Tellet sends:
* The full transcript, including interviewer questions and respondent answers in the order they were spoken or typed.
* The interview language.
* Timestamps for each spoken turn, when audio is available.
* A link to the audio recording for spoken interviews. CoLoop fetches the audio file directly. The link expires shortly after use to keep the recording secure.
* A stable identifier, so sending the project again updates the existing CoLoop transcript.
Tellet does not send personal data collected in screening questions, such as name or contact details, unless that data appears inside the interview itself.
## Reconnect if credentials expire
CoLoop credentials can expire. When that happens, Tellet shows a banner on **Settings** > **Integrations** and on linked projects:
> CoLoop has revoked or expired the credentials. Reconnect to resume pushing transcripts.
Click **Reconnect to CoLoop** in Tellet and sign in again. Existing Tellet project links are preserved, so you only need to reconnect once.
## Disconnect CoLoop
To stop Tellet from sending transcripts to CoLoop:
1. In Tellet, open the organization menu.
2. Click **Integrations**.
3. On the CoLoop card, click **Disconnect**.
Disconnecting CoLoop removes the CoLoop credentials from Tellet and clears every Tellet project's CoLoop link. It does not delete transcripts already in CoLoop.
You can reconnect later, but you need to link each Tellet project to a CoLoop project again.
## Daily sending limit
Tellet limits how many transcripts one organization can send to CoLoop each day. If you reach the limit, sending pauses until the following day. Anything still queued resumes after the limit resets.
If you need to send a large batch, such as a completed study with thousands of interviews, contact Tellet support before you start.
# Webex
Source: https://docs.coloop.ai/integration/integration/webex
Learn how to add CoLoop to a Webex meeting, record interviews, and upload to a project instantly.
CoLoop can be integrated directly with Webex to capture and record interviews live as they are conducted. The recordings will be kept within the project you’ve selected and take away the layer of uploading videos to CoLoop. This can help to streamline the operational process and improves speaker accuracy particularly when conducting focus groups with multiple participants.
## **CoLoop Recorder Key Information for Webex**
**Supported Features**
* Full support for standard Webex meetings.
* Scheduling in advance supported.
**Limitations & Requirements**
* Active speaker events availability:
* Only available when the meeting host has a **paid** Webex account and enables **closed captions** turned on.
* Without active speaker data, transcripts will not be diarized, resulting in null speaker labels.
* Audio limitations:
* Webex provides only one combined audio stream—individual speaker audio tracks are not available.
* Video limitations:
* Webex provides only one combined video stream.
* No support for configurable or alternative video layouts.
* Chat messages:
* Bots currently cannot send chat messages in Webex meetings.
## How to Use CoLoop Recorder with Webex
You can record Webex meetings in CoLoop in two ways. You must have a project to upload the recordings into and all calendar invites must have a Teams link for the recorder bot to join.
### **Create a project in CoLoop**
1. Open the project you're recording an interview for within CoLoop ([Creating a project](/docs/setting-up-a-project/create-a-project) for more information.)
### Invite the Recording Bot using one of Two Methods
**+Join Meetings**
You can have CoLoop join meetings ad-hoc or right before meetings start by entering in the meeting URL after clicking 'Join meeting.'
2. Click on the '+' sign next to the Meetings tab on the left hand menu.
3. In Webex, copy the meeting link and paste the invite into the URL box.
4. Enter a name for the meeting to name the file once it's uploaded.
5. Select now for the CoLoop Recorder bot to join immediately or select later and enter in the time. CoLoop recorder will wait in the waiting room for 10 minutes once the call starts.
**Project Specific Email Invite**
Create an email address for specific CoLoop projects and add that email to all associated calls.
This method is ideal for adding CoLoop to multiple meetings or for allowing third parties to schedule calls by using the project-specific email.
1. Navigate to the **Meetings** section in CoLoop.
2. Select **Email Invite** and create an email address for the project.
### Allow the recording bot into the call
* At this point we recommend ensuring you have obtained permission to record from your participants
* Allow the meeting bot to record the meeting.
* The **CoLoop Recorder** will start recording soon thereafter.
### Viewing Recordings
* After you have finished the meeting, CoLoop will automatically import the meeting recording.
* To view the meeting recording, navigate to **Files** tab in your project.
* From here simply follow the steps to transcribe your file ([Creating a transcript](/docs/setting-up-a-project/create-a-transcript))
### **Managing Meeting Bot Settings**
Meeting bot settings can be managed on an organisation level, or on a project level.
Video Output:
* In meetings by default, CoLoop will appear on the screen as another participant. To turn this off please toggle it off under 'Video Output'.
**Organisation Level:**
Making changes at an organisational level will make those changes effective across every single project.
**Project Level Management:**
Making changes at the project levels will affect all call recordigns associated with that project only.
# Yazi
Source: https://docs.coloop.ai/integration/integration/yazi
Yazi is an asynchronous, AI moderated tool for conducting qual at scale studies via WhatsApp. Follow the guides below to upload outputs from Yazi directly into CoLoop for analysis.
# Zoom
Source: https://docs.coloop.ai/integration/integration/zoom
Learn how to add CoLoop to a Zoom meeting, record interviews, and upload to a project instantly.
CoLoop can be integrated directly with Zoom to capture and record interviews live as they are conducted. The recordings will be kept within the project you’ve selected and take away the layer of uploading videos to CoLoop. This can help to streamline the operational process and improves speaker accuracy particularly when conducting focus groups with multiple participants.
## **CoLoop Recorder Key Information for Zoom**
**Supported Features**
* Works with Zoom meetings, and webinars where registration is not required.
* For Zoom meetings, the bot does not require host permission in order to join or record. This means whoever is running the call does not need to be the same as the person that created the call.
* Scheduling in advance supported.[****](/integration/integration/google-meet#create-a-project-in-coloop)
**Limitations**
* Meetings requiring registration are not supported.
* Breakout rooms are not supported.
* The bot cannot bypass the waiting room. Users must always make sure to admit the bot to the call to initiate recording.
## How to Use CoLoop Recorder with Zoom
You can record Zoom meetings in CoLoop in two ways. You must have a project to upload the recordings into and all calendar invites must have a zoom link for the recorder bot to join.
### **Create a project in CoLoop**
Open the project you're recording an interview for within CoLoop ([Creating a project](/docs/setting-up-a-project/create-a-project) for more information.)
### Invite the Recording Bot using one of Two Methods
**+Join Meeting:**
You can have CoLoop join meetings ad-hoc or right before meetings start by entering in the meeting URL after clicking 'Join meeting.'
1. Click on the '+' sign next to the Meetings tab on the left hand menu.
Copy the link from Zoom:
2. In the Zoom app, copy the meeting link by clicking **Invite** followed by **Copy invite link**.
3. Paste the meeting invite into the box in Join Call
4. Enter a name for the meeting
5. CoLoop Recorder will instantly join the meeting URL as a participant and will wait up to 15 minutes in the waiting room.
**Project Specifc Email Invite**
Create an email address for specific CoLoop projects and add that email to all associated calls.
This method is ideal for adding CoLoop to multiple meetings or for allowing third parties to schedule calls by using the project-specific email.
1. Navigate to the **Meetings** section in CoLoop.
2. Select **Email Invite** and create an email address for the project.
### Allow the recording bot into the call
* At this point we recommend ensuring you have obtained permission to record from your participants
* Allow the meeting bot to record the meeting.
* The **CoLoop Recorder** will start recording soon thereafter.
You can verify the meeting is being recorded by checking the **recording icon** is present next to **CoLoop Recorder** participant in the **Participants** view.
### Viewing Recordings
* After you have finished the meeting, CoLoop will automatically import the meeting recording.
* To view the meeting recording, navigate to **Files** tab in your project.
* From here simply follow the steps to transcribe your file ([Creating a transcript](/docs/setting-up-a-project/create-a-transcript))
### **Managing Meeting Bot Settings**
Meeting bot settings can be managed on an organisation level, or on a project level.
Video Output:
* In meetings by default, CoLoop will appear on the screen as another participant. To turn this off please toggle it off under 'Video Output'.
Gallery View Recording:
* If you want CoLoop to record a zoom gallery view, rather than the individual speakers then you can enable the toggle. *Please note recording in gallery view will negatively impact on-screen concept tests using slide decks as stimuli as these must be visible on the full screen when using CoLoop for concept analysis.*
Meeting Bot Permissions:
* Admins can enable bots to enter sign-in required meetings without host approval. Please note this does not bypass the Zoom waiting room. Please see the article [here](https://coloop-knowledge-base.help.usepylon.com/articles/3086972735-zoom-sign-in-required-meetings-settings) for more information on this.
Webinars:
* CoLoop recording bot can be set to record the gallery view, the default setting is speaker view. Zoom Webinars where registration is not required are supported.
**Organisation Level Management:**
Making changes at an organisational level will make those changes effective across every single project.
**Project Level Management:**
Making changes at the project levels will affect all call recordings associated with that project only.