Qualitative research with real people, run from your AI agent or your code. Ask a question about your customers or shoppers; get AI-moderated interviews (typically 20–30 minutes, laddering 5–7 levels deep) and findings with verbatim quotes linked to each interview.
Participants come from a vetted 4M+ consumer panel or from your own customers, by voice, chat or video in 80+ languages. Paid launches stop for a human to approve the plan and the quote. How quality is controlled · Pricing
| skills | Run qualitative research with real people: AI-moderated in-depth interviews, concept tests, and prototype tests. Agent Skills and plugins for Claude Code, Claude Desktop and claude.ai, ChatGPT (plugin), Codex, Cursor (plugin) and any agent that reads Agent Skills. |
| examples | TypeScript examples for the API and MCP server: create a study, launch against a saved estimate, and retrieve findings with quotes. Runs without an account in fixture mode. |
| Docs | MCP server, API reference and the skills library. |
Website: userintuition.ai