WriteChoice validator

Test if your docs isready for AI agents

Paste a docs portal URL to score structure, crawlability, and agent readiness in minutes. You'll get prioritized issues, a concise fix brief, and a result you can share with your team.

Portal health

91/100

Representative score across recent WriteChoice audits.

Snapshot

Confidence snapshot

Audits in scope12

Ready docs0

Readiness ratio68%

Signals reviewed

llms.txt presence and crawlability

Markdown delivery and structure

Navigation, freshness, and access rules

Potential follow-up buckets11

Consistent scoring

Compare releases and portals with the same evaluation logic every time.

Built for follow-through

Save results, revisit progress, and keep teams aligned on the same brief.

Saved audits

Reopen past validations

Keep a running history of docs quality, revisit past findings, and show progress release over release.

Methodology

How each audit is scored

Each run fetches the docs directly and applies the same evaluation logic so teams can benchmark quality, prioritize fixes, and measure progress over time.

Sample10 linksPacing100msTimeout15sModeDeterministic

llms.txt and Discovery

Verifies whether agents can discover your documentation index, follow the links it exposes, and find llms.txt from the pages you publish.

Markdown Delivery

Checks whether the site offers clean markdown through .md URLs or content negotiation instead of forcing agents through bloated HTML.

Page Size

Measures whether pages fit within agent context windows and whether the useful content starts early enough to avoid truncation.

Content Structure

Evaluates tabs, headers, and code fences to ensure the content remains parseable after an agent converts or serializes the page.

URL Stability

Confirms that documentation URLs resolve cleanly, return correct status codes, and avoid redirect behavior that can confuse crawlers and agents.

Observability

Compares freshness and parity signals so agent-facing content stays accurate across llms.txt, markdown output, and cached HTML responses.

Authentication

Tests whether agents can access the docs without hitting auth walls, or whether alternate public paths exist when the main site is gated.