Open AI Crawl Control for the domain, find Operator in the Crawlers table and set its Action to Block. If it is not listed, add a custom rule that blocks requests whose user agent contains “Operator”.
You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/crawlers/operator/cloudflare with the UI removed — the content only. A browser asking for the same address gets the full designed page.
Operator is a crawler run by OpenAI. It reads pages at the moment a person asks a question, to answer it.
Cloudflare does not hold a site’s robots.txt; the origin does. But it can add to that file, and it can refuse a crawler before the origin is ever asked.
A group that names a crawler replaces the * group for that crawler; it does not add to it. Paths the * group closes are open to a crawler with its own group unless they are repeated there.
robots.txt at the origin, refusing Operator:
User-agent: Operator Disallow: /
robots.txt at the origin, allowing Operator:
User-agent: Operator Allow: /
The edge answers first. If Cloudflare blocks Operator, an Allow in robots.txt changes nothing: the crawler is refused before the origin is asked. A site that allows a crawler on paper and blocks it at the edge is a site that crawler never reads.
Yes. A Block in AI Crawl Control or in a custom rule is answered by Cloudflare itself, and the request never reaches the origin. “Operator” is an ordinary word and “contains” would match it inside any user agent, so use the crawler’s own entry in AI Crawl Control rather than a custom rule.
A 200 means the name is let through; a 403 means something in front of the page refuses it. This tests the name from your own address. A platform that checks a crawler’s address as well may treat the real Operator differently.
The request:
curl -I -A "Operator" https://your-site.example/
Open AI Crawl Control for the domain, find Operator in the Crawlers table and set its Action to Block. If it is not listed, add a custom rule that blocks requests whose user agent contains “Operator”.
In AI Crawl Control set Operator to Allow, and check under Security → Settings that the AI bot setting is not blocking it.
Yes. A Block in AI Crawl Control or in a custom rule is answered by Cloudflare itself, and the request never reaches the origin. “Operator” is an ordinary word and “contains” would match it inside any user agent, so use the crawler’s own entry in AI Crawl Control rather than a custom rule.
No. Googlebot goes by its own name and follows its own rules; a group or a firewall rule for Operator does not apply to it.
Citable strips the UI from a website for AI agents and serves them only the content.
When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.
How it works: https://getcitable.in/how-it-works · Summary for AI agents: https://getcitable.in/llms.txt
Source: https://getcitable.in/crawlers/operator/cloudflare · Citable · Run the free audit · llms.txt · getcitable@gmail.com