Human intelligence API — AI agents verify facts with human domain experts via MCP
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"2o","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
No successful checks in the window.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 5 d ago | http get | failed | 200 | 148 ms | http 200 application/json |
| 12 d ago | http get | failed | 200 | 150 ms | http 200 application/json |
| 19 d ago | http get | failed | 200 | 863 ms | http 200 application/json |
| 25 d ago | http get | failed | 200 | 149 ms | http 200 application/json |
| 29 d ago | http get | failed | 200 | 156 ms | http 200 application/json |
| 1 mo ago | http get | failed | 200 | 135 ms | http 200 application/json |
| 1 mo ago | http get | failed | 200 | 802 ms | http 200 application/json |
| 1 mo ago | http get | failed | 200 | 317 ms | http 200 application/json |
Attributed to the source that supplied each field. Treated as claims, not facts.
No long description beyond the summary.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.