pingfusi is an MCP that lets AI agents call human reviewers.
Think MTurk for AI agents. With pingfusi your agent can:
- Get a second opinion: a real person looks at the work, not another model
- Get human judgment: where opinion is the answer — design taste, wording, which version people prefer
- Skip the iteration loop: the agent revises, another human checks each round, and you only see the finished version
Set up Pingfusi for your coding agents with a single command.
npx pingfusi setupHere are some example prompts you can try with the pingfusi MCP.
| feedback about | example prompt | what you get | demo |
|---|---|---|---|
| playtest | get 3 playtesters on mygame.itch.io/demo. use pingfusi |
a playtest report from real players | https://pingfusi.com/playtest |
| a confusing page | Is my pricing page confusing anywhere? use pingfusi |
comments pinned to what's off | |
| a website clone | Clone www.example.com pixel-perfect. use pingfusi |
a perfectly cloned website | copy-anything.com |
| design taste | Make my website not look like AI slop. use pingfusi |
design feedback | video |
| video vibes | Does my promo video look right? use pingfusi |
feedback pinned to timestamps |
Each of these publishes the work first so the reviewer can open it; when in doubt, publish: a reviewer can only judge what they can see. Text-only questions work too — if words can carry the whole question, the reviewer just sees the question.
Every job is the same loop underneath:
- File a review — the agent pushes the work (a built site, a video, any artifact) so the reviewer can open it, then files a review with concrete steps to check and what counts as approval.
- A human reviews — a real person opens the work and sends back pinned comments anchored to the exact elements that are off.
- You get better output — the reviewer's comments land in the agent's context, so the next version is shaped by real human feedback.
Example: you ask for a landing page that doesn't look like AI slop. The agent publishes it, a reviewer answers "gradient looks template-y" and "too much padding under the hero". The agent fixes both and refiles; the next reviewer approves. You come back to a page a human signed off on.
The full command lives in docs/COMMANDS.md.
pingfusi setup install + onboarding
pingfusi doctor check the install; prints a fix per problem
pingfusi ask "<question>" ask a human reviewer, from any directory
pingfusi studio [ping_id] local viewer for playtest & review results —
sessions, recordings, transcripts, agent findings
MIT