The AI research toolkit: skills, prompts & workflows
Everything you need to run AI-powered research: from ready-to-use Claude skills and copy-paste prompts to MCP integrations and workflows built by practitioners.
New: Synthetic user skill and Great Question MCP skills, dropped July 2026.
Get the AI research toolkit
What's inside One toolkit, four ways to use AI in research
Skills you install, prompts you copy-paste, and integrations that connect your research stack.
Claude skills for research
Pre-built skills that turn Claude into a research assistant. Transcript cleaning, synthesis, discussion guide generation, and more: install once, use on every project.
Research prompt library
Copy-paste prompts for every stage of the research lifecycle: from planning and recruiting to analysis and stakeholder readouts. Tested on real research projects.
MCP integrations
Connect Claude directly to Great Question and your research tools. Pull study data, query your repository, and automate workflows without leaving your AI workspace.
Research workflows
End-to-end workflows for common research patterns: rapid synthesis of 50+ interviews, automated tagging, cross-study pattern identification, and insight distribution.
Connect your research platform directly to Claude
Great Question's Model Context Protocol server gives Claude direct access to your research data: studies, participants, insights, and your entire repository. No more copy-pasting between tools.
- Query your research repository from Claude: “What did customers say about onboarding in Q4?”
- Pull participant data and study results into AI analysis workflows.
- Automate insight tagging, highlight extraction, and cross-study synthesis.
- Works with Claude Desktop, Claude Code, and any MCP-compatible client.
Run this command in Claude Code to add Great Question as an MCP server.
claude mcp add --transport http great-question \ https://greatquestion.co/api/mcp/v1
Skill library Research skills you install once and use forever
Each skill packages expert-level instructions so Claude handles research tasks the way a senior researcher would. Install with one command.
Transcript cleaner
Transform messy interview transcripts from Otter, Fireflies, or Zoom into clean, analysis-ready documents. Speaker normalization, filler removal, structural formatting.
Research synthesizer
Synthesize findings across multiple interviews or studies. Identifies patterns, contradictions, and key themes, then generates a structured summary with evidence.
Discussion guide builder
Generates semi-structured discussion guides from research objectives. Includes warm-up questions, core topics with probes, and closing protocol.
Insight tagger
Automatically tag and categorize research highlights. Maps quotes to themes, tracks sentiment, and builds a structured taxonomy across your entire study.
Stakeholder readout
Turns raw research findings into polished stakeholder-ready readout decks. Tailors framing for PMs, designers, and leadership: different audiences, different emphasis.
Screener builder
Creates participant screening criteria and surveys from target persona descriptions. Includes qualification logic, red-flag disqualifiers, and scoring rubrics.
Affinity mapper
Run digital affinity mapping on research data. Groups observations into clusters, suggests category names, and highlights outliers worth investigating.
JTBD analyzer
Reads transcripts (or notes) and produces a structured JTBD analysis. It writes a core job statement in Moesta's “when… I want to… so I can…” format, maps push/pull/anxiety/habit forces with evidence and quotes from the transcript.
Research brief writer
Generates research briefs from a business question. Recommends methodology, defines success criteria, estimates timeline, and scopes participant requirements.
JTBD interview guide builder
Generates a complete JTBD moderation guide based on the Competing Against Luck methodology. It builds out the six-stage timeline walkthrough with opening questions and 3 to 4 probes per stage, includes a four forces deep-dive section (push, pull, anxiety, habits).
Survey designer
Builds a research-quality survey from a clearly stated goal. It structures the survey with a context-setter, behavioral anchors, core questions, and an open-ended closer. It picks response formats that actually match the research question (frequency scales for behaviors, Likert for opinions, NPS for advocacy, max-diff for ranking).
Great Question MCP skills
We now have 6 skills that work directly with our MCP: Interview study builder, Unmoderated test builder, Recruiter, Study email writer, Stakeholder readout generator, Panel hygiene auditor.
Synthetic user skill
Brand new: Builds grounded synthetic users (reusable customer profiles) from a connected research repository, where every attribute traces back to real interview sessions.
Prompt library Copy-paste prompts for every research stage
Tested on real research projects. Each prompt includes context-setting, specific instructions, and output formatting so Claude knows exactly what you need.
Planning
Works for generative, evaluative, and mixed-method studies.
I'm planning a [method] study about [topic]. My research questions are [X]. Generate a research brief with methodology justification, participant criteria, timeline, and risk factors.
Recruiting
Pairs with the Screener Builder skill for automated workflows.
Create a screener survey for [target persona]. Include 8-10 questions that filter for [criteria]. Flag red-flag responses that indicate poor fit. Output as a table I can paste into Great Question.
Analysis
Best with 5-15 transcripts; use the Synthesizer skill for 15+.
Here are transcripts from [N] interviews about [topic]. Identify the top themes with supporting quotes, note contradictions between participants, and flag surprising findings I should investigate further.
Synthesis
Cross-study synthesis: one of AI's strongest research applications.
Compare findings from these [N] studies conducted over [time period]. What patterns are consistent? What's shifted? Generate a longitudinal insight map with confidence levels.
Stakeholder communication
Customize framing for PMs, designers, or leadership audiences.
Turn these research findings into a 1-page executive summary for [audience]. Lead with the 3 most actionable insights, include supporting evidence, and end with recommended next steps.
Repository
Builds on the Insight Tagger skill for ongoing repo management.
Review these [N] research highlights and generate a consistent tagging taxonomy. Map each highlight to themes, assign sentiment, and identify which insights connect across multiple studies.
People building great AI research resources
We're not the only ones thinking about this. Here are practitioners and builders pushing AI + research forward.
Caitlin Sullivan
AI Customer Research · Ex-Head of User Research at Spotify Business
14+ years in customer insights, now teaching teams how to build AI-powered research systems with Claude Code. Her Maven courses cover building validated insight systems: skills, slash commands, and workflows that run with minimal effort. She's run 550+ hours of AI tests for customer research and trained teams at YouTube, Canva, Meta, and Figma.
Noam Segal
AI Insights Manager, Figma
Noam Segal is an AI Insights Manager at Figma and founder of the AI Insights Lab community. A trained psychologist who's led research at Airbnb, Meta, and Intercom, he now studies how AI reshapes the way product teams learn from users.
Go deeper on AI in research
Our five-part series on AI in UX research, plus feature deep-dives and practical guides.
How to use AI for UX research: the complete guide
The full picture: when AI helps, when it doesn't, and how to integrate it into your workflow without compromising research quality.
Read
AI for research planning & recruiting
How AI changes the front half of research: from writing briefs and screeners to finding the right participants faster.
Read
AI analysis & synthesis: a 6-step pipeline
A practical pipeline for using AI to process qualitative data: from transcript to tagged insight to cross-study pattern.
Read
AI for research knowledge management
How to build a research repository that actually gets used, with AI handling tagging, retrieval, and insight surfacing.
Read
Try AI-moderated interviews
Extend qualitative research beyond limits with the reach of a survey and the depth of an interview. Coming soon to Great Question.
Try it
Introducing Great Question AI
How Great Question's built-in AI handles synthesis, tagging, and cross-study analysis, without needing a separate AI tool.
ReadGet the blog in your inbox
Latest insights for customer-obsessed product builders. Once a month, no noise.