AI Product Index / llms.txt published
It is the first file an arriving agent fetches after robots.txt, and the only one whose entire purpose is to tell a model what you are. Absent, the agent has to infer your site from HTML written for humans.
Publish /llms.txt: an H1 with the site name, a > blockquote summary, then linked sections of the pages agents should read.
# /llms.txt — publish at {{ORIGIN}}/llms.txt
# Your Product Name
> One sentence on what this is and who it is for.
## Docs
- [Getting started]({{ORIGIN}}/docs/start): what it says on the tin.
- [API reference]({{ORIGIN}}/docs/api): endpoints, auth, limits.
## Contact
- [Email](mailto:you@example.com)
Free, no signup, same endpoint that produced every grade on the leaderboard:
curl "https://index.percall.dev/api/score?url=https://your-site.example"
It returns the letter grade and every check by name with pass/fail. The
$0.05 call at POST /api/audit adds why each one failed and a
snippet with your origin already in it.