# 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. A populated analysis grid: participant rows down the left, an Overview row at the top, and four columns of different output types (a written synthesis column, a Yes/No column, a numeric column, and a categorization column), with the Add a Question Column pill at the bottom of the screen ## 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**. The All Analysis Grids page with two creation cards side by side, Analysis grid on the left and Full content analysis report on the right, each showing a preview above its name and description, and the My analysis grids section below them 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. The Create new grid dialog with the Custom grid card selected and expanded, showing the Select rows step with the From participants, From segments, and From existing grid options ## 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. The Add Participant & Segment Rows dialog on the Add many tab, with the search box at the top and several participants and segments checked in the list below ### 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. The Build custom row tab with two segments selected and the AND operator between them, and the Create more toggle switched on in the footer ### 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). The expanded question composer at the bottom of the grid with a question typed in, the output type gallery unfolded above it showing the five cards Synthesis, Quotes only, Numeric, Yes / No and Categorization, and the Add column button on the right ### 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. The question composer with Categorization selected: a question typed at the top, a Labels row with four label chips and a + button, the Mutually exclusive checkbox on the right, and the Categorization, Add filter, Advanced and Add column controls along the bottom **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. The Add Question Column dialog with the advanced panel open on the right, showing the Overview prompt text area filled with a custom instruction and the Skip overview checkbox below it ### 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. The two-pane Create from discussion guide view: the Suggested and Extracted tabs with a multi-select list of questions on the left, and the editor for the focused question on the right showing its prompt, output type and labels ### 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. The cell details panel open beside the grid for an Overview cell of a categorization column, showing the Row filter, a Participant distribution table listing each label with its percentage bar and participant count, and below it the individual participant answers behind the selected label ### 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). The grid with two panels open to the right: the cell details panel showing an Overview cell's full themed output, and the Citation sources panel listing the participants behind the selected finding, with the cited passage highlighted in one quote and an Open button beneath it ## 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 | A grid with two filter chips and a sort chip in the bar above it, the Overview row relabeled Filtered overview with a Compute button, and one column's cell reading Not computed with a Compute button revealed on hover ## 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 | The display settings modal: the Grid, Segments and Evidence panel preferences as labeled switch cards down the left with a description under each, a mock analysis grid previewing the current choices on the right, and Cancel and Save in the footer ### 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? Screenshot 2025-10-27 at 21.04.18.png 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. ![An Analysisgridevidence](https://cdn.coloop.ai/mintlify-coloop-docs/images/an_analysisgridevidence.png) ## Renaming a grid Rename grids to keep things organized by clicking the 3 dots next to the page name. ![Screenshot 2025-10-27 at 20.42.42.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-10-27at20.42.42.png) ## 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. ![](https://cdn.coloop.ai/mintlify-coloop-docs/images/docs-assets/analysis/image-46.png) ### 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. ![Screenshot 2025-10-27 at 21.03.15.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-10-27at21.03.15.png) Or do this from the Analysis Grids section. ![Screenshot 2025-10-27 at 20.58.44.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-10-27at20.58.44.png) # 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. ![Screenshot 2025-08-26 at 10.38.22.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-08-26at10.38.22.png) ## 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?" Screenshot 2025-09-01 at 17.37.49.png **Qunatiative Queries: Numerical Outputs & Proportion Bars** * Example Prompt: "How many participants said their families influenced their voting decisions?" Screenshot 2025-09-01 at 17.44.23.png **Concept Testing: Sentiment Tables** * Example Prompt: "Conduct concept analysis on #Novartis" Screenshot 2025-09-01 at 17.40.21.png **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" Screenshot 2025-09-01 at 17.52.23.png 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. Screenshot 2025-09-01 at 17.56.08.png **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" Screenshot 2025-10-28 at 13.14.16.png ### 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. A Chatfilteringedit # 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 Screen Recording 2025-10-24 at 12.36.39 PM.gif ## 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. ![Finalfinalnozoomes Gi](https://cdn.coloop.ai/mintlify-coloop-docs/images/finalfinalnozoomes.gif) ### 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'. Screenshot 2025-12-01 at 09.25.03.png **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. ![Screenshot 2025-12-01 at 09.26.50.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-12-01at09.26.50.png) 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. ![Screenshot 2025-12-01 at 09.20.19.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-12-01at09.20.19.png) **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. ![Screenshot 2025-12-01 at 09.18.02.png](https://cdn.coloop.ai/mintlify-coloop-docs/images/Screenshot2025-12-01at09.18.02.png) ### 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. ![Full clip storage.gif](https://cdn.coloop.ai/mintlify-coloop-docs/images/Fullclipstorage.gif) ## 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. ![](https://cdn.coloop.ai/mintlify-coloop-docs/images/docs-assets/analysis/image-64.png) ![](https://cdn.coloop.ai/mintlify-coloop-docs/images/docs-assets/analysis/image-65.png) ![](https://cdn.coloop.ai/mintlify-coloop-docs/images/docs-assets/analysis/image-66.png) ## 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. ![clips final .gif](https://cdn.coloop.ai/mintlify-coloop-docs/images/clipsfinal.gif) 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. ![Clips Filter Segments (1).gif](https://cdn.coloop.ai/mintlify-coloop-docs/images/ClipsFilterSegments%281%29.gif) 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. ![exportedclips.gif](https://cdn.coloop.ai/mintlify-coloop-docs/images/exportedclips.gif) ## 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.