Enter your URL to get an instant AEO score — schema markup, llms.txt, and AI crawler access.
5 free checks per day — no account required
What we check
Schema Markup
JSON-LD structured data: Organization, FAQPage, Article, Product schemas. AI engines use these to understand and cite your content.
LLMs.txt
/llms.txt is the AI equivalent of robots.txt — it tells AI engines what your product does and which pages to index.
AI Crawler Access
We simulate GPTBot, ClaudeBot, PerplexityBot, and 5 other AI crawlers to check if they can actually reach your site.
Answer engines do not return ten links. They assemble one answer and cite a handful of sources, so being usable as a source is the whole game. Three technical signals decide whether you qualify, and this check scores each of them separately so you can see which one is holding the number down.
Whether GPTBot, ClaudeBot, PerplexityBot and Google-Extended are permitted in robots.txt. A blocked bot cannot cite you at all, which is why this is weighted heaviest.
Whether your pages carry schema an engine can parse — Organization, FAQPage, Product. Without it a model infers what you do from prose, and frequently gets it wrong.
A plain-text file at your root pointing models at your highest-value pages. The newest of the three signals and still rare, so usually the cheapest points to gain.
It is a 0-100 readiness score for whether answer engines can use your site as a source. This checker averages three independent sub-scores: whether AI crawlers are allowed to fetch your pages, whether your structured data lets an engine state who you are, and whether an llms.txt file points models at your most useful content. A high score means engines are able to cite you; it does not by itself mean they currently do.
Crawler access is weighted most heavily, because a blocked bot makes everything else irrelevant — it counts the share of major AI bots your robots.txt permits, then adds credit for a discoverable llms.txt and a valid sitemap. Schema and llms.txt quality are scored separately and the three are averaged into the headline number. Grades run A at 80 and above, B at 65, C at 50, D at 35, and F below that.
The bots that actually fetch pages on behalf of answer engines: GPTBot and OAI-SearchBot for ChatGPT, ClaudeBot for Claude, PerplexityBot for Perplexity, Google-Extended for Gemini and AI Overviews, plus Applebot and the common research crawlers. Each is checked against your live robots.txt, and blocks are reported per bot rather than as a single pass or fail.
It is free and needs no account. Enter a domain and the score comes back immediately. Results are cached per domain for 24 hours and checks are rate limited per IP, which is what keeps the tool fast and free to run.
Work in the order the score is weighted. Unblock the AI crawlers in robots.txt first, because nothing downstream can help while engines are shut out. Next add Organization and FAQPage structured data so an engine can describe your business without inferring it from prose. Publish an llms.txt file last — it is the cheapest of the three to add and still uncommon, so it is often the fastest points gained.
No, and the distinction matters. This score measures whether engines can reach and parse you, which is a precondition for citation rather than proof of it. Whether you are actually named is measured by running real buyer-intent prompts through each engine and counting how often your brand appears against competitors — that is a MentionShare scan, not a readiness check.