Index #1 · rank 20 of 47 · AI · scanned 2026-07-19
Mistral AI
Agent readability of https://docs.mistral.ai/ — scored from a reproducible crawl snapshot under rubric v0.
Deterministic · 40%
79
LLM rubric · 35%
67
Task probes · 25%
100
Band
green
Machine-checkable fundamentals
✓llms.txt at the rootllms.txt present · 2 sections · 75 links82%
✕OpenAPI spec discoverable & validOpenAPI found (https://docs.mistral.ai/openapi.yaml) but did not validate40%
✓Heading structuremean heading-quality 74% over 60 pages74%
✓Code samples on reference pages54/59 reference pages have code samples92%
✓Auth documented with an exampleauthentication documented with a code example100%
✓Pages within agent token budget54/60 pages within 8000-token budget90%
✓Links resolve0/4969 links broken100%
✓Crawler & meta hygienemean meta-hygiene 60% over 60 pages60%
Can an agent actually finish?
✓Find the authentication methodnamed an auth method with a cited sourcePASS
✓Find the rate limitsstated a concrete rate limit with a cited sourcePASS
✓Construct a first valid requestproduced a request construct with a cited sourcePASS
Executed by a pinned claude-sonnet-5 agent over the crawl snapshot; graded on substance + citation, transcripts stored.
Prose quality, graded by model
Clarity
2.5/4
Completeness
2.7/4
Consistency
2.8/4
Key pages assessed
6
Is this your documentation? Every score is reproducible from stored inputs, and corrections are part of the methodology — if a page we couldn't reach is reachable to a normal agent, we'll re-scan and publish the update. See the methodology or grab your badge.