AI · RANK #39 OF 51
Pipeboard is Murky to agents.
Discry independently scored how well an AI agent can discover and understand the Pipeboard API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 30% · what a model knew before reading the docs
Discovery
42 / 100OpenAPI specno publicly accessible spec foundFail
llms.txt20 described linksPass
llms-full.txtnot presentFail
AGENTS.mdno github org knownFail
.well-known/mcp.jsonnot presentFail
MCP registrynot found in probed registriesFail
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapincludes docs pagesPass
Comprehension
59 / 100Factual recall1/2 passed
Absence honesty1/1 passed
Where agents fail
How are this API's model identifiers written (give one exact example model id)? — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.