GEO Ready Checker: Can AI Read and Cite Your Site?

Enter a page and we fetch it as ChatGPT, Claude, Perplexity, Google and Copilot do, then run 56 checks across crawler access, firewalls, content without JavaScript, indexing, structured data and llms.txt. You get a score out of 100, the evidence for each check and fixes you can copy and paste.

What We Check

Each check is labelled with how strong the evidence is: documented by the AI platforms themselves, supported by research, good practice, or speculative. The score leans on what is documented. Read the full methodology.

  • Group A · 25% of the score

    AI crawler access (robots.txt)

    Documented by every platform.

  • Group B · 15% of the score

    Live access, firewall and CDN

    Documented, and the most common silent failure.

  • Group C · 5% of the score

    llms.txt and markdown for agents

    Speculative for search, useful for agents.

  • Group D · 15% of the score

    Content visible without JavaScript

    Most AI fetchers do not run JavaScript.

  • Group E · 15% of the score

    Indexability and AI-use directives

    Google AI features need indexable, snippet-eligible pages.

  • Group F · 8% of the score

    Structured data and entities

    Hygiene: the effect on citations is not proven.

  • Group G · 8% of the score

    Content extractability

    Titles, headings and alt text are scored. Editorial patterns are shown but not scored, as no format guarantees a citation.

  • Group H · 5% of the score

    Trust and entity signals

    Hygiene.

  • Group I · 4% of the score

    Performance basics

    Hygiene.

Honest About the Evidence

Plenty of GEO advice is guesswork. We only score heavily what the platforms document: their crawlers must be allowed in robots.txt and through your firewall, the content must be in the HTML because most AI fetchers do not run JavaScript, and Google's AI features need an indexable page that may show snippets. Structured data and llms.txt are checked, but weighted lightly, and editorial patterns such as FAQs are shown without being scored. The checks follow our SEO and GEO Website Build Standard.

How We Fetch Your Page

Requests come from our server with each crawler's published user agent, one at a time and a moment apart, and our own bot reads robots.txt, the sitemap and llms.txt. We never fetch private addresses and follow at most five redirects. About our bot.

Questions and Answers

What is GEO?

GEO (generative engine optimisation) is the work of making a website easy for AI search engines and assistants such as ChatGPT, Claude, Perplexity, Google AI Overviews and Copilot to find, read and cite. Most of it is technical SEO done well: crawlers must be allowed in, the content must be in the HTML and the page must be indexable.

What does the GEO ready score mean?

It is a weighted score out of 100 across nine groups of checks. 90 or more is GEO ready, 75 to 89 is nearly there, 50 to 74 needs work and under 50 means some AI engines probably cannot see the page at all. Serious problems, such as blocking an AI search crawler or a noindex tag, cap the score whatever else passes. The methodology page lists every check, its weight and its evidence.

Does llms.txt help my site appear in AI answers?

There is no good evidence that it does today. Google has said its AI features do not need it, and studies of AI citations found no measurable effect. It can help AI agents and coding tools that read it, so we check it, but the whole llms.txt group is only 5% of the score.

Why does the checker say a crawler is possibly blocked when the site works in my browser?

Firewalls and CDNs such as Cloudflare, Vercel and AWS often block requests that say they are an AI crawler but come from an ordinary data centre. We send each crawler’s real user agent from our own server, so a block we see may only affect imitations, and the real crawler (verified by its IP addresses) may get through. Check your firewall logs for the real bots before changing anything.

Should I block AI training crawlers?

That is a business decision, and the checker does not mark you down for it. Blocking a training crawler such as GPTBot, ClaudeBot or Google-Extended does not remove you from ChatGPT search, Claude search or Google AI Overviews, which use other crawlers. Blocking the search crawlers (OAI-SearchBot, Claude-SearchBot, PerplexityBot, Googlebot and Bingbot) does.

Do you store my results?

Each result is saved for 12 months at its own link so you can share it and re-run it. Results stay out of search engines unless the owner makes a result of 75 or more public. We do not store your IP address, only a hashed version used for rate limits. Your name and email are only taken if you ask for the PDF.

How is this different from your Chrome extension?

The Chrome extension checks the page you are looking at, inside your browser. This checker fetches the page from our server as eight different AI crawlers, so it can also catch firewall blocks, robots.txt rules and content that only appears with JavaScript.

More free tools

  • AI Crawler Checker

    Can each AI crawler get to your site? robots.txt rules and live fetches as eight AI bots, in about ten seconds.

    Open
  • llms.txt Validator

    Check an llms.txt against the format, with line numbers, the Lighthouse audit, broken links and prompt injection.

    Open
  • llms.txt Generator

    Draft an llms.txt for your site from its sitemap, ready to edit and publish.

    Open
  • AI Crawler List

    Every AI crawler user agent, who runs it, what it is for and whether it obeys robots.txt, from the official docs.

    Open
  • Chrome Extension

    Our free GEO and AI visibility checker for Chrome: check any page you are looking at in one click.

    Open