How verification works
Any program can put “GPTBot” in its User-Agent. The only reliable proof is the source IP address. The tool compares the address with the lists published by the companies themselves, refreshed daily: OpenAI (GPTBot, OAI-SearchBot, ChatGPT-User), Anthropic (one list shared by its crawlers), Perplexity, Google (Googlebot), Microsoft (Bingbot), Apple (Applebot), Mistral AI, Common Crawl (CCBot) and DuckDuckGo (DuckAssistBot). Where a publisher documents reverse DNS verification, the tool checks it too, with forward-DNS confirmation.
- Genuine: the address belongs to the claimed crawler's official ranges.
- Spoofed: the claimed crawler publishes its ranges and the address is not in them. You can block it without hurting your visibility.
- Unverifiable: the publisher provides neither IP ranges nor a DNS method.
The Observatory statistics use exactly the same method. To automate this check, use the API.
More free tools
Free AI visibility checker
Check for free whether ChatGPT, Claude, Perplexity and Gemini can read and cite your website - robots.txt, llms.txt, JavaScript and hidden text.
AI robots.txt generator
Build a robots.txt in one click that blocks AI training while keeping your site visible in ChatGPT Search, Claude and Perplexity. Free.
robots.txt tester for AI crawlers
Paste your robots.txt and instantly see, crawler by crawler, whether GPTBot, ClaudeBot, PerplexityBot or Google-Extended can access a page.
Free llms.txt generator from your sitemap
Generate a draft llms.txt in the llmstxt.org format from your website's sitemap - titles, descriptions and sections ready to review.
Free prompt injection detector
Check whether a web page or a text hides instructions aimed at AI assistants - hidden text, HTML comments and invisible Unicode characters.