GEO Audit
AI crawlers do not run JavaScript, and they read your page in a different order than a person does. Paste a URL and see exactly what they get.
Audits one page, plus your site's robots.txt, llms.txt and sitemap.
Fetching the page the way a crawler does…
What your robots.txt tells each AI crawler
What the crawler reads
Every check
This checks one page. Run it across your whole site with ContextBolt SEO inside Claude, Cursor, or Codex, next to live keyword, SERP, and backlink data. $35/month.
What a GEO audit checks
GEO stands for generative engine optimization. It is the work of getting your pages into AI answers, and it splits cleanly in two. Are you mentioned, and can the crawler use your page in the first place. This tool does the second half.
Four questions, in the order they stop mattering. Can AI reach the page, can it read it, can it understand what the page is about, and could an agent operate it. A page that fails the first question cannot be helped by anything it does well in the other three.
Why the word count is usually the surprise
The crawlers that feed AI answers fetch your HTML and do not render it. No JavaScript runs. If your page builds its content in the browser, the crawler receives an empty shell, and no amount of good writing inside that shell counts. That is why this audit shows you the text it actually received rather than a checkmark. Some well-known sites hand a crawler twenty words.
Blocking AI crawlers is three decisions, not one
Most robots.txt files that block AI block all of it, usually by accident. Training crawlers like GPTBot and CCBot feed model training. Search crawlers like OAI-SearchBot and PerplexityBot fetch pages so they can cite them in answers. User agents like ChatGPT-User fetch a page because a person asked the assistant to read it. Blocking the first is a policy. Blocking the second means you cannot be cited. Blocking the third means a person who chose your link gets nothing.
What this tool does not tell you
It does not tell you whether AI currently mentions your brand. That is the other half, and the free AI visibility checker answers it by reading real ChatGPT and Google AI answers. A page can be perfectly readable and still never get cited, and it can be cited today and become unreadable tomorrow. Both are worth watching.
It also audits one page rather than a site. Robots, llms.txt and the sitemap are site-wide, but the headings, the structured data and the word count belong to the URL you gave it. Running the same checks across every page, on a schedule, is what ContextBolt SEO does from inside your agent.
Frequently asked questions
What is a GEO audit?
A check of whether AI assistants can reach your page, read it, understand it, and act on it. It is the technical half of getting cited in AI answers.
How is it different from an SEO audit?
An SEO audit asks whether Google can rank the page. A GEO audit asks whether an AI crawler can use it. AI crawlers mostly do not run JavaScript, read structured data first, follow their own robots.txt rules, and browsing agents drive a page through its accessibility tree rather than its layout.
Does it run JavaScript?
No, on purpose. GPTBot, ClaudeBot and PerplexityBot fetch the HTML and do not render it, so this fetches your page the same way. The word count you see is the text those crawlers receive.
Is it free?
Yes. No signup, no email. A URL's result is cached for 24 hours, so re-running the same page returns the stored result instead of crawling the site again.
Why did it say it could not read my page?
Bot protection refused us. That is not proof that ChatGPT or Claude are blocked, since their crawlers sit on allow-lists that ours does not. When it happens the audit reports no score rather than guessing one. The robots.txt rules it shows are still real.
Should I block AI crawlers?
It depends which. Blocking training crawlers is a legitimate choice. Blocking search crawlers means you cannot be cited in an answer. Most sites blocking everything did not mean to separate the two.
Does it audit my whole site?
No, one URL, plus the site-wide robots.txt, llms.txt and sitemap. For every page on a schedule, ContextBolt SEO runs these checks from inside Claude, Cursor or Codex.