How do I use Ask AI?

With Marvin’s Ask AI, you can answer any question using research from across your repository*. Gain customer insights into everything: from features customers want, to learning how they use your product in existing workflows.

Just type your question, and Marvin will scan all the data to which you have access. It'll surface and collate relevant data to help you synthesize the insights you need to answer the question.

For example, "What do customers say about our onboarding?" or "Which customers want more payment options." You can add filters to only search among surveys, and even time filters to search across specific time periods.

You can use Ask AI in two modes, depending on the kind of answers you need.

In this mode, Marvin generates a quick response from a subset of the most relevant data.

We recommend you use when you need answers quickly. Such as when you’re conducting discovery or exploring a topic. Marvin will help you identify starting points for your research. Check the linked sources to read notes, files, and view clips from interviews to gain deeper insights. You can also ask follow-up questions to focus on specific details.

Query in Think Fast mode every time you need quicker answers. When you have more detailed questions, you can switch to the other mode.

It uses Marvin’s Agentic Ask AI to generate in-depth answers with insights from across your entire repository. Multiple AI research agents work together to transform years of customer knowledge into comprehensive, evidence-backed answers.

The Agentic Ask AI questions itself to ensure it provides the best possible answer. This way, you can connect all your customer research and data across tools to a custom LLM that helps you shape product, sales, and marketing decisions.

Every response links directly to your interview transcripts, support tickets, sales calls, notes, and documents, so you can verify everything yourself.

You can learn more about Agentic Ask AI in our help center article.

You can use Ask AI effectively at every stage of your research project.

Ask questions about your existing research to form a hypothesis or outline the scope of the project.

You can also identify participants who you’ve interviewed before and meet the criteria for your new project. Use the information to write project overviews and discussion guides.

Type in questions in the Ask AI bar on your home page. Marvin will surface insights based on the most relevant data in your repository.

It'll open up the Ask AI modal.

Or you can also go to the Discover Research tab.

to query the data in interviews, surveys, usability tests, etc. Marvin will check the context of the recordings, images, and documents to surface relevant insights.

Under the tab Q/As, you’ll see key points from the call tagged to specific questions.

Click My topics to see insights grouped by topic, theme or use-case. The default topics available for each call are listed under Pre-made topics. Feedback for Researcher will contain helpful guidance and suggested questions for the person moderating the call.

Painpoints & Concerns and Key Takeaways will group relevant information from the call under these topics.

Marvin will consider your discussion guide and labels to create accurate summaries and find relevant insights.

You can uncover trends, find themes in the data, prove or disprove your hypothesis, locate quotes, etc. Use the Analyze tab to run Ask AI on the data within a project. You can add the answers to Insights to create reports to share with your team.

You can also use Ask AI while analyzing notes across multiple projects in Cross project analysis.

To get relevant answers more easily, make sure you apply the right filters. Marvin will then be able to provide more targeted results. You can filter by project, file tags, research areas, time and even the file type.

You can choose to surface insights only from participants and filter out responses from interviewers. Click the settings toggle and make sure the Participants option is set to Respondents.

With this option selected, Marvin still uses interviewer questions for context, but highlights participants' opinions in answers. You can use this to make sure interviewers opinions are not highlighted as insights. Respondents is the default option unless changed by you.

Once you type your question, Marvin will start scanning relevant data to put together an answer. You'll be able to see the thinking process to understand how the AI arrived at the answer.

You can navigate away from the tab while Ask AI runs in the background. You can set up notifications for Marvin to play a sound when the answer is ready.

Once the answer is generated, you can verify the information or gather more detail from the source by clicking the in-line citations. It'll take you to the exact clip or line in the file Marvin used to synthesize the insight. You can read more about citations in our help center article.

You can ask follow-up questions on an Ask AI result to refine the answer. You can use a range of prompts. Here are some suggestions:

This is not an exhaustive list. We encourage you to explore Ask AI till you have the insights you need.

If you apply a filter after the answer is generated, Marvin will add to the answer in the same chat.

Marvin will also retain a history of your Ask AI results. You can access these quickly from the advanced search page. Find searches categorized by time period: last 7 days, 7-30 days, and older than 30 days.

You can navigate to the advanced search page from the modal.

With Ask AI integrated into Slack, your teammates can search for insights in the tools where they already work. They don't have to hunt for research to take decisions backed by customer evidence.

All roles on Standard and Enterprise plans can use Marvin’s Ask AI in any channel or direct message on Slack. It will gather insights from the projects to which you have access in Marvin to give you an answer directly in Slack.

Enterprise accounts can extend Ask AI on Slack to anyone in their organization, even if they don't have an account on Marvin. To do this, an Enterprise Admin must share research with the entire organization from Admin settings. This can only be enabled for accounts that have a single team. It is currently not possible to enable this access for companies that have multiple teams within the same account.

All non-Marvin teammates will be considered guest/temporary users. They will see answers based on research that is public and shared with everyone in the team.

You can ask questions in any channel or DM.

To query Ask AI, use command /heymarvin or /research and type your question. Here are some examples of the questions you can ask.

/heymarvin What did users say about new features in the June 2025 NPS survey?

/research Summarize the 5 most recent Sales Team stand-ups.

Marvin will collate an answer based on research you have access to in Marvin. Whether you ask in a channel or a DM, Marvin will share the answer with everyone in the chat.

You'll see an overview, key takeaways, and supporting quotes (if available and relevant).

You can even ask follow-up questions to dive deeper into the data or refine your query. Just select Ask a Follow Up. Marvin will retain the context from your previous question to generate a new answer.

With Marvin, you can easily share all AI analysis with the rest of your team.

You can send anyone a link to a result. Just click Share chat and select Copy share link. Viewers will still be able to read and copy analysis as well as sources, but not ask follow-up questions.

You can also share answers to any Slack channel. Select Post answer to Slack at the bottom of the answer or in the Share chat menu at the top. Then choose the Slack channel to which you want to share analysis.

Want to learn about the kind of prompts you can use on Ask AI? Check out our help center article.