AI crawlers · Answer engines

`Gemini-Deep-Research`

Gemini-Deep-Research is the user-triggered fetch run by Google: Gemini research agent. Its operator publishes no IP ranges or DNS names for it, so a request carrying this name cannot be verified. Treat the name in a log line as a claim.

User-agent token	`Gemini-Deep-Research`
Operator	Google
What it does	Gemini research agent
Kind	user-triggered fetch
Can a request be verified?	No — user agent string only
In a CrawlCheck scan	Read from robots.txt; a refusal is scored

Allow or block it in robots.txt

User-agent: Gemini-Deep-Research
Disallow: /

User-agent: Gemini-Deep-Research
Allow: /

Add a group that names it: "User-agent: Gemini-Deep-Research" followed by "Disallow: /". A crawler follows only the most specific group that names it, so once a group names Gemini-Deep-Research, rules under "User-agent: *" no longer apply to it; repeat in that group any Disallow lines you still want.

What blocking it changes

Yes. It is how Google reaches a page to answer a question at the moment a person asks, so refusing it stops that engine reading the site.

Other agents from Google

Google-CloudVertexBot — Vertex AI grounding
Googlebot — Google Search / AI Overviews
Google-Extended — Gemini training
Googlebot-Image — Google image crawler
Googlebot-News — Google News
Googlebot-Video — Google video crawler
Storebot-Google — Google Shopping
Mediapartners-Google — Google AdSense
APIs-Google — Google push delivery
GoogleOther — Google non-search fetch
AdsBot-Google — Google Ads quality
Google-Agent — Google user-triggered agent, acts on the web
Google-GeminiNotebook — Gemini Notebook user-supplied URL fetch
GoogleOther-Image — Google common crawler, public image URLs
GoogleOther-Video — Google common crawler, public video URLs

See what Gemini-Deep-Research and every other named agent receive from your own site: run a free scan. The full catalogue is on AI crawlers and as JSON at /ai-crawlers.json.

Questions about Gemini-Deep-Research

QHow do I block Gemini-Deep-Research in robots.txt?

QHow can I tell if a request from Gemini-Deep-Research is real?

Its operator publishes no IP ranges or DNS names for it, so a request carrying this name cannot be verified. Treat the name in a log line as a claim.

QDoes blocking Gemini-Deep-Research affect whether my site appears in AI answers?

Yes. It is how Google reaches a page to answer a question at the moment a person asks, so refusing it stops that engine reading the site.

QDoes CrawlCheck test my site as Gemini-Deep-Research?

Not as a request. CrawlCheck reads the rules your robots.txt sets for Gemini-Deep-Research and reports them. A refusal of it counts toward the grade, because it costs the site visibility.