Autonomous agents
Operator is a bot operated by OpenAI that browses the web on its own to finish multi-step tasks. Operator is an AI agent created by OpenAI that can use a web browser. Whether it honours robots.txt is undocumented, and a request claiming to be Operator can be checked against a published IP range file.
Request says
"Operator"
Checked against
OpenAI's published IP ranges
Live check
Paste the address from the log line. It is checked against what the operator publishes.
Reference
| User agent | OperatorToken only: match on the substring. |
|---|---|
| Operator | OpenAI |
| Purpose | Autonomous agents |
| Respects robots.txt | No policy |
| Verification method | IP rangesPublished IP range file Browser-driving agent run on behalf of a signed-in user. OpenAI lists the matching egress range file in its bots documentation. |
| Crawl pattern | Not published |
| Robots.txt tokens | Operator |
| Operator documentation | https://platform.openai.com/docs/bots |
Operator is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf of a human user.
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: Operator
Disallow: /User-agent: Operator
Allow: /User-agent: Operator
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking Operator stops automated sessions that fill forms, click through flows and read pages the way a logged-in user would. Rate limits and challenges usually work better here than a robots.txt line.
Build a file for every crawlerFAQ
Operator is a bot operated by OpenAI that browses the web on its own to finish multi-step tasks. Operator is an AI agent created by OpenAI that can use a web browser. Whether it honours robots.txt is undocumented, and a request claiming to be Operator can be checked against a published IP range file.
Not documented. No operator statement says whether Operator reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
Browser-driving agent run on behalf of a signed-in user. OpenAI lists the matching egress range file in its bots documentation. The reference is published at https://platform.openai.com/docs/bots.
Add the Operator token to robots.txt with Disallow: /. If the crawler ignores robots.txt, match the user agent at your CDN or reverse proxy and return 403 there instead.
Blocking Operator stops automated sessions that fill forms, click through flows and read pages the way a logged-in user would. Rate limits and challenges usually work better here than a robots.txt line.