LLMCheckBot

What it fetches

LLMCheckBot runs only when someone submits a URL on llmcheck.app. It never crawls on a schedule and never follows links across the web. For one analysis it may request, from the submitted site only:

• The submitted page, plus robots.txt, llms.txt and sitemap.xml.
• Up to two pages linked from that page where a customer would book, buy, sign up or get in touch.
• A few well-known locations that describe how software can connect to a site, such as /openapi.json and /.well-known/openid-configuration.

That is at most about a dozen requests per analysis, no more than four at a time, each abandoned after five seconds. It reads public pages only. It does not log in, submit forms, or run JavaScript.

Why

LLM Check tells brands whether AI assistants can find them and act on them. The Agent Readiness check looks at a site the way an AI agent would: can it reach the pages, understand what is sold, and complete a task like booking or ordering. The results are shown only to the person who ran the analysis. Read more on our methodology page.

How to block it

LLMCheckBot honours robots.txt. To keep it off your whole site, add:

User-agent: LLMCheckBot
Disallow: /

To keep it away from one area only, disallow that path instead. Changes take effect on the next analysis; nothing is cached on our side beyond the analysis itself.

Questions

If you think the bot misbehaved, contact us with the time and the URL and we will look into it.