Free tool
Can AI search find and quote your page?
Enter a URL and this free analyzer checks whether ChatGPT, Google AI Overviews, Perplexity, Claude and Copilot can reach the page, read it without JavaScript and quote it - and lists what to fix first. No sign-up, nothing stored.
One page per scan. Nothing is stored. Takes 5-20 seconds.
What does it check?
Crawler access
robots.txt rules for 14 AI and search crawlers, and the page requested as GPTBot, ClaudeBot, PerplexityBot, Googlebot and Bingbot - to catch CDN or firewall blocks that robots.txt does not show.
Content without JavaScript
How many words are in the HTML the server sends. OpenAI's, Anthropic's and Perplexity's crawlers do not run JavaScript.
Indexing signals
noindex, nosnippet, canonical pointing to the home page or into a redirect, repeated or unfilled titles, sitemap and honest lastmod dates.
Citable content
One H1, question-style headings, a direct opening answer, numbers, dates and links to sources - the changes that measurably increased citations in research.
Structured data
JSON-LD that does not parse, ratings with no visible reviews, logo URLs that return 404, and markup Google has retired.
AI files
Whether llms.txt and ai-catalog.json exist and are well formed - reported as optional, because their effect is unproven.
Each finding is labelled by how solid the advice behind it is: Official (platform documentation), Research (measured studies), Practice (practitioner experience) or Disputed.
What can't it measure?
It cannot see what the rest of the internet says about you - mentions, reviews, directories, communities, video - and that is the strongest signal for being recommended by an AI assistant. It also scans one page at a time and does not ask the assistants themselves. Its crawler requests do not come from the vendors' IP ranges, so a firewall that verifies bots by IP may block the test even when it lets the real crawlers in; the report says when that could be the case.
Questions
What is AEO and GEO?
Answer Engine Optimization and Generative Engine Optimization: making your content easy for AI assistants and AI search (ChatGPT, Google AI Overviews and AI Mode, Perplexity, Claude, Copilot) to find, understand and cite. Google's own guidance is that this is still SEO - there is no special markup or file that switches it on.
What does this analyzer check?
Whether AI crawlers may and can fetch the page (robots.txt per bot, and the page requested with each crawler's User-Agent), how much text exists before JavaScript runs, noindex and nosnippet, canonical errors, title and headings, whether the text answers directly with numbers, dates and sources, structured data errors, and the AI files llms.txt and ai-catalog.json - the last two by the same rules as Lighthouse's agentic browsing audits.
Why is there no single AI score?
Because readiness, presence and impact are different things. A page can be perfectly readable and still never be recommended, because assistants weigh what other sites say about a brand. The tool scores readiness per area and lists what it cannot measure.
Does blocking GPTBot remove me from ChatGPT?
No. OpenAI, Anthropic, Google and Apple separate training crawlers from search crawlers. Blocking GPTBot, ClaudeBot or Google-Extended opts out of model training; ChatGPT search uses OAI-SearchBot and Claude uses Claude-SearchBot, and Google AI features use the normal Googlebot index.
Do I need llms.txt or schema markup?
Neither is required. Google says you don't need special AI files or markup to appear in its AI features, no major AI company has committed to reading llms.txt, and a large Ahrefs study found no significant effect of schema on AI citations. Both are cheap, low-priority extras.
Is my URL or report stored?
No. The scan runs once and the report exists only in your browser tab. There is no database and no account.
Built by Miloš Leković, Cypress Tech
Based on platform documentation from Google, OpenAI, Anthropic, Microsoft and Perplexity and published research, checked on . Want the fixes done for you?