How agent-ready are your docs?
Your documentation has AI readers now.
Docs for Agents runs the same five-task reading test against a product’s public docs with a panel of three AI models, then publishes the scorecard and the receipts.
Every report ends in a scorecard.
Strong quickstart, one concrete rate-limit number in 144 pages, and it lives under Metrics.
Ships .md mirrors, llms.txt, and an MCP server, and its two webhook pages name the same parameter two different ways.
The docs give instructions to the reading agent itself, and the classic quickstart path graded PARTIAL partly because of it.
Five first-hour jobs, graded pass, partial, or fail.
Send the first email, find the rate limits, recover from a 429, run webhooks end to end, use the primary SDK. Each panelist attempts the battery alone, using only what the public pages say, and every verdict needs a verbatim quote and its URL.
How the test worksThe agent infrastructure is ahead of the content that feeds it.
All three pilot products ship llms.txt, markdown mirrors, a live MCP server, and an embedded docs assistant. None of the three cleared the reading test without a PARTIAL.
How agent-ready are your docs?
Agent-ready documentation gets an AI agent from zero to a correct integration using only what the pages say. The test measures that directly: five first-hour developer jobs, three models grading independently, five readiness checks on the agent-facing surface, and a verbatim receipt behind every claim. The scorecard shows where an agent passes, guesses, or stalls.
Frequently asked questions
Is this an execution test?
No. It is a reading test: no accounts are created, no API calls run, and no code executes. A PASS means the public docs got an agent to a confident, unambiguous answer.
Which models are on the panel?
GPT 5.6 Sol, Claude Opus 5, and DeepSeek v4 Flash, run independently on an identical brief with no shared context. The panel stays fixed so scores stay comparable, and any membership change is disclosed on the affected scorecard.
Why do the panelists disagree?
Different models read differently, and disagreement is printed on the scorecard rather than averaged away. A page contradiction that splits the panel is usually the most useful finding in the report.
What is the Agent-Ready Grade?
Fifteen reading votes at PASS 2, PARTIAL 1, FAIL 0 make 30 points, five readiness checks at 10 points each make 50 more, and the total out of 80 becomes a US school letter grade with its percentage. The docs platform is recorded but never graded.
Can you test our docs?
Nominate the docs site on the nominate page. The test runs one product at a time, using public pages only.
The next report needs a nominee.
Nominate a docs site