Skip to main content
Once connected, you talk to your research in plain language — your MCP client translates that into the underlying tool calls. Here are common ways teams put it to work. Prep for a stakeholder readout Pull recent studies, surface key highlights and insights, and get transcript excerpts, all without leaving your AI tool. Ask something like: “Summarize the top findings from our onboarding study and pull the strongest supporting quotes from transcripts.” Set up a study from scratch Create an interview, survey, or unmoderated study, add screener questions with qualification logic and skip branching, assign moderators, configure the interview calendar, customize the invitation email, and send invitations to candidates — all through natural language prompts. Ask: “Create a new round robin interview study about onboarding with a $25 Amazon gift card incentive and a 10-participant cap, add a 5-question screener with skip logic, and invite our enterprise candidates.” Start a study from a saved template Skip rebuilding a screener question by question — find an existing template and apply it to a new or existing study instead. Ask: “Find our onboarding interview screener template and apply it to this new study.” Build an unmoderated test Stand up a prototype test, website test, card sort, or tree test by adding and ordering blocks. Try: “Create an unmoderated study with a card sort of these 12 features into 4 categories, then add a follow-up open text question.” Catch up on research you missed Search across studies and transcripts to quickly get up to speed. Try: “What studies have been completed in the last month? Give me a summary of each.” Find patterns across participants Chain candidate lookups with transcript searches to spot themes. Example: “Which participants mentioned pricing concerns? What studies were they in, and what exactly did they say?” Pull supporting evidence for a product decision Search the whole repository at once, across sessions, highlights, reels, insights, uploaded files, and survey results, to build a case grounded in research. Ask: “Find all highlights related to navigation issues and summarize the common themes.” Code a study as you read it Have your AI tool work through a study’s transcripts, creating highlights and applying your team’s existing tags as themes emerge, so the study ends up coded in Great Question instead of a spreadsheet. Try: “Go through the transcripts in our checkout study. Highlight every moment where a participant hesitates at payment and tag each one with our ‘Checkout friction’ tag.” Turn a finding into an insight Save your synthesis back to the repository so teammates (and their agents) can find it later. Ask: “Write this up as an insight titled ‘Users don’t trust the payment step’ and embed the three strongest highlights as evidence.” Build a reel for stakeholders Assemble the strongest highlights on a theme into a shareable video reel without clipping by hand. Try: “Find the highlights tagged ‘Onboarding confusion’ from Q3 and compile the five clearest ones into a reel.” The reel’s video is stitched in the background, so it may take a few minutes to be ready to play. Only highlights with a video clip can go in a reel; a highlight made on a transcript without timings, or on a session with no recording, can’t. Review Screener Responses Pull a study’s screener responses to see how candidates qualified. Screener responses are read one study at a time. Try: “Show me all screener responses for our pricing study. How many were qualified vs. disqualified, and which answers most often led to disqualification?” Responses include each candidate’s answers, qualification status, and match score, so your AI tool works out the reasons from the answers. Review a participant’s history Find the research sessions and highlights a participant appears in across your repository. Try: “Find every session and transcript with participant Jane Doe and summarize what she told us.” A candidate’s profile also shows when they were last contacted. Manage your research panel Create and update candidate profiles, manage custom attributes, target saved segments, and ensure GDPR compliance with delete capabilities. Ask: “Update the department attribute for all candidates from the Q1 onboarding study to ‘Product.’” Your AI tool updates candidates one at a time, so large batches take longer and can run into the MCP rate limit of 60 requests per minute. Still need help? Contact us at support@greatquestion.co — median response time is 19 minutes during support hours.