OpenAI
OAI-SearchBot
Discovers content for ChatGPT search results.
AI searchUser-requested fetch
ChatGPT-User
Fetches pages for user actions in ChatGPT and custom GPTs.
Operated by OpenAI
See your agent traffic PurposeUser-requested fetch
HTTP identifierChatGPT-User
IdentityVerify beyond the name
THE SIGNAL
What this visit tells you
A verified fetch can reflect a user asking ChatGPT to retrieve a page. Nearby requests alone do not identify one person or one task.
Requested public pages
Public-page 403 and 404 responses
Subsequent page requests
Your next move
Inspect the requested public page and next requests. A 403 can interrupt research; a 404 can indicate an outdated or guessed URL.
The technical details
MarkdownHow to identify it
Look for the ChatGPT-User identifier in a request’s User-Agent. This is a name match, not identity verification. Version strings may change.
How to check identity
Compare the request IP with the current operator-published ranges linked in the source. A matching name alone does not verify identity.
Access and robots.txt
User-initiated requests may not follow robots.txt.
Seeing 403 or 404 responses?
403 means access was denied; 404 means the resource was not found. Compare the public path, request time, edge security event and origin response to find the cause.
Separate intended restrictions and secret-file probes from pages that should work. A User-Agent name alone does not justify allowing a request.
SourcesReviewed 2026-09-14
Identity and purpose are based on these sources. Analytics interpretation and suggested checks are Apostl guidance.
APOSTL PulseSee ChatGPT-User in context
See their requests. Find the pages that matter.
See your agent trafficKEEP EXPLORING
Different bots, different intent
Anthropic
Claude-User
Retrieves web content in response to Claude users.
User-requested fetch