Assistant fetchers
Gemini-Deep-Research is a bot operated by Google that fetches single pages on demand for an AI assistant. Gemini-Deep-Research is the agent responsible for collecting and scanning resources used in Google Gemini's Deep Research feature, which acts as a personal research assis…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Request says
"Gemini-Deep-Research"
Checked against
Nothing published
Live check
No operator check exists for Gemini-Deep-Research. This still shows what the address really is.
Reference
| User agent | Gemini-Deep-ResearchToken only: match on the substring. |
|---|---|
| Operator | |
| Purpose | Assistant fetchers |
| Respects robots.txt | No policy |
| Verification method | Claim onlyNone published, user agent only No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. |
| Crawl pattern | Not published |
| Robots.txt tokens | Gemini-Deep-Research |
| Operator documentation | https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers |
Gemini-Deep-Research is the agent responsible for collecting and scanning resources used in Google Gemini's Deep Research feature, which acts as a personal research assis…
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: Gemini-Deep-Research
Disallow: /User-agent: Gemini-Deep-Research
Allow: /User-agent: Gemini-Deep-Research
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking Gemini-Deep-Research means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.
Build a file for every crawlerFAQ
Gemini-Deep-Research is a bot operated by Google that fetches single pages on demand for an AI assistant. Gemini-Deep-Research is the agent responsible for collecting and scanning resources used in Google Gemini's Deep Research feature, which acts as a personal research assis…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Not documented. No operator statement says whether Gemini-Deep-Research reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
You cannot, at least not from the request itself. No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. Compare the source IP against hosting and datacenter ranges instead, and rate limit anything that behaves like a crawler.
Add the Gemini-Deep-Research 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 Gemini-Deep-Research means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.