Are you letting
the bots in?

Paste any URL. In under 10 seconds, find out which AI engines can reach, read, and cite your site, and what's quietly blocking them.

Free, no account, no email required. Nothing about your site is stored, scans run fresh every time.

Or compare it against up to two competitors →

Six categories. One score.

Every deduction maps to a named finding. Full mechanics, exact point values, and how each check works: how it works →

28 pts Access The gate. robots.txt per-bot verdicts, server-level block detection (WAF/CDN comparison), sitemap reachability, and meta robots signals. If crawlers can't reach you, nothing else matters. 18 pts Authority & entity The signals AI weighs most when deciding who to cite. sameAs links to Wikipedia, Wikidata, LinkedIn; named author attribution; Wikidata knowledge graph presence; About page. 16 pts Structured data How confidently AI models parse and attribute your content. JSON-LD presence and coverage of high-value types: Organization, FAQPage, Article, WebSite, and more. 14 pts Readability Can AI crawlers actually read your content? JavaScript-rendering dependence and login/paywall gating, two ways a "reachable" site is still effectively invisible. 14 pts Extractability Is your content quotable? Heading hierarchy, answer-first structure, question-style headings, lists and tables: the formats AI engines cite most readily. 10 pts Freshness & hygiene Date signals, llms.txt, canonical tags, HTTPS, response speed, and sitemap lastmod. Recency and technical cleanliness matter, especially for time-sensitive citations.

Want to see how you compare? Score your site against up to two competitors →

Made for the same problem I had.

I work on SEO and GEO at Akamai, and built this on nights and weekends because I couldn't find a free checker that explained why a site failed, not just that it did. No pricing page, no plans to add one.

Read the full story →

Understand what's happening before you change anything.

Guides that cover the actual mechanics, not another list of tips.

Start here What is GEO? The six signals that determine whether AI engines can cite you, and how they differ from traditional SEO. Technical robots.txt for AI bots Which user agents control ChatGPT, Claude, Perplexity, and Gemini citations, and the wildcard mistake that blocks all of them. Deep dive How AI citations work The retrieval-augmented generation pipeline that powers AI answers, and what actually drives whether you get cited. Technical Structured data for AI Which schema.org types move the needle, how to implement them in JSON-LD, and the mistakes that reduce citation confidence. Technical What is llms.txt? The file that gives AI systems a structured overview of your site: format, examples, and whether it actually matters. Reference GEO glossary 40+ definitions: OAI-SearchBot, Claude-SearchBot, RAG, entity signals, and every term you'll encounter in AI search optimization.

Common questions, straight answers.

Can ChatGPT find my website?

ChatGPT uses OAI-SearchBot to index content for real-time citations. This is a different crawler from GPTBot (which is for training). If your robots.txt blocks OAI-SearchBot, or has a wildcard rule that catches it, ChatGPT cannot cite your site, regardless of how relevant your content is. Paste your URL above to check in under 10 seconds.

Does blocking GPTBot hurt my AI visibility?

No, not directly. GPTBot is OpenAI's training crawler. Blocking it limits what GPT models learn during pre-training, but has no effect on real-time citations. The citation pipeline uses OAI-SearchBot, which is a separate user agent. Many sites that blocked GPTBot (a defensible choice) accidentally also blocked OAI-SearchBot because they used wildcard disallow rules. We check both.

Why doesn't my site appear in AI answers?

The most common causes, in order of frequency:

  • Blocked crawler. Your robots.txt has a wildcard or per-bot rule blocking the AI retrieval crawler.
  • JavaScript-only content. Your content loads via client-side JavaScript. Most AI crawlers fetch raw HTML only.
  • Missing entity signals. No structured data, no Wikidata presence, no named authorship, so AI systems treat you as an anonymous source.
  • noindex tag. A meta robots noindex directive on pages that should be publicly citable.

We check all four as part of the free scan.

What is GEO, and is it different from SEO?

GEO (Generative Engine Optimization) is the practice of making sure AI search engines can find, read, and cite your content. It's related to SEO but distinct in important ways. Traditional SEO asks: can Google rank this page? GEO asks: can AI systems extract a citable answer from it? The technical requirements differ: AI crawlers often don't render JavaScript, entity authority matters more than backlinks, and content structure for quotability differs from content structure for dwell time. Our GEO guide walks through all six signals.

How is letthebots.in different from other SEO tools?

letthebots.in specifically checks AI search visibility, not traditional SEO ranking factors. It evaluates per-bot access (which AI crawlers can reach you), content readability for AI parsers, structured data coverage, entity authority signals, content extractability, and freshness indicators. These are the signals that determine whether AI engines cite you, which traditional SEO tools don't measure.

Which AI crawlers should I allow in robots.txt?

To be citable by each major platform, you need to allow these retrieval crawlers:

  • OAI-SearchBot: ChatGPT citations
  • Claude-SearchBot: Claude citations
  • PerplexityBot: Perplexity citations
  • Googlebot: Gemini / Google AI Overviews
  • Bingbot: Microsoft Copilot

The training crawlers (GPTBot, ClaudeBot, Google-Extended) are separate. Blocking those is fine; it only affects model training, not citations. See our full robots.txt guide.

What is llms.txt and should I have one?

llms.txt is a plain-text file at yourdomain.com/llms.txt that gives AI systems a structured summary of your site: what it does, who runs it, and what the key pages are. It was proposed in 2024 and is increasingly checked by Perplexity and other AI engines during indexing. Creating one takes under 20 minutes and contributes to your freshness and hygiene score. It won't fix access or readability problems on its own, but it helps once the bigger issues are resolved. See our llms.txt guide.

Is my data stored when I run a scan?

No. letthebots.in is stateless by design. Scans run fresh every time and nothing about your site is stored between sessions. If you subscribe to the newsletter or ask us to monitor a site, we store that email address in our own Cloudflare KV store, never a third-party marketing platform, until you unsubscribe.

What does the score of 85+ (Citation-Ready) mean?

A score of 85 or above earns the Citation-Ready badge. It means your site passes all critical GEO signals: AI crawlers can reach you, your content is readable without JavaScript rendering, you have JSON-LD structured data covering key types, your entity is identifiable (sameAs links, authorship), your content is structured for extraction, and your date signals are current. Sites at this level are well-positioned to be cited when AI engines encounter relevant queries.