PersonaLab builds a pool of personas grounded in real U.S. demographics, interviews the ones that fit what you're building — up to ten at once — and hands you a report where every insight is traced back to who said it.
How it works
No research background needed. You describe, the personas talk, you get something you can act on.
Say what you're building and who you want to learn from. We narrow to that demographic and rank every persona by fit — strong, moderate, weak — so you can see who's worth asking. Up to 100 in a pool.
One question goes to every persona you picked. Their answers land side by side, in their own voice — built to disagree, not to please you. Up to ten questions per study.
How many would actually use it (19 of 30, not a projection), common ground, key differences, recommended actions — and every line links back to the exact answer it came from.
Why you can trust it
The fair question about AI personas is “why would I believe them?” Here's the honest answer.
In your editor
Already working in Claude Code, Cursor, or Codex? Connect PersonaLab over MCP and your personas become people you can talk to mid-build. Casual interviews are free; a full study costs the same 1 credit per persona it does here.
claude mcp add --transport http --scope user personalab https://personalab.aimgonna.com/api/mcp