AI-readable guidance validator
Validate whether your website exposes a useful llms.txt file for AI crawlers, answer engines, and agentic discovery workflows.
AI guidance file validator
The scan reads llms.txt as a guidance document, then validates it against emerging and established standards, then checks whether nearby crawl policy and discovery signals support what the file is trying to tell AI systems.
# Site guidance for AI systems
> Key pages, source material, policies, and crawl notes.
## Important resources
- [Guide](/blog): implementation guidance
- [Blog](/blog): source articles
- [Contact](/contact): publisher signal
The focused scan checks /llms.txt and validates it against the emerging and established standards plus nearby crawler and discovery signals that affect whether AI systems can use it.
A useful llms.txt file should explain what the site is, which pages matter, and how agents should interpret important resources.
The report checks whether crawler policy conflicts with the guidance you are giving in llms.txt.
Missing links, thin descriptions, blocked crawler paths, weak sitemap discovery, and unclear resource lists can all reduce AI readability.
The result uses the same assessment suit as full CanAgentUse reports, and provides status, evidence, issue details, and fix guidance.
After validating llms.txt, run the full readiness scan to test APIs, auth discovery, MCP, structured data, accessibility, and action readiness.
FAQ
llms.txt is an emerging root-level markdown file that gives AI systems concise guidance about important pages, source material, policies, and site structure.
No. robots.txt controls crawler access rules, while llms.txt gives AI-readable guidance. Good AI visibility often needs both to be consistent.
