Index #1 · rank 45 of 47 · Data · scanned 2026-07-19
Databricks
Agent readability of https://docs.databricks.com/ — scored from a reproducible crawl snapshot under rubric v0.
Deterministic · 40%
58
LLM rubric · 35%
58
Task probes · 25%
33
Band
amber
Machine-checkable fundamentals
✓llms.txt at the rootllms.txt present · 16 sections · 251 links100%
✕OpenAPI spec discoverable & validOpenAPI found (https://docs.databricks.com/api/openapi.json) but did not validate40%
✓Heading structuremean heading-quality 100% over 1 pages100%
✕Code samples on reference pagesno reference pages identified0%
✕Auth documented with an exampleno page documents authentication0%
✓Pages within agent token budget1/1 pages within 8000-token budget100%
✓Links resolve0/1 links broken100%
✕Crawler & meta hygienemean meta-hygiene 30% over 1 pages30%
Can an agent actually finish?
✓Find the authentication methodnamed an auth method with a cited sourcePASS
✕Find the rate limitsanswer states no concrete numeric rate limitFAIL
✕Construct a first valid requestno source page citedFAIL
Executed by a pinned claude-sonnet-5 agent over the crawl snapshot; graded on substance + citation, transcripts stored.
Prose quality, graded by model
Clarity
3/4
Completeness
1/4
Consistency
3/4
Key pages assessed
1
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.