Assistant fetchers
AI2Bot-DeepResearchEval is a bot operated by Ai2, a non-profit AI research institute that fetches single pages on demand for an AI assistant. Ai2Bot-DeepResearchEval is operated by Ai2, a non-profit AI research institute. 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
"AI2Bot-DeepResearchEval"
Checked against
Nothing published
Live check
No operator check exists for AI2Bot-DeepResearchEval. This still shows what the address really is.
Reference
| User agent | AI2Bot-DeepResearchEvalToken only: match on the substring. |
|---|---|
| Operator | Ai2, a non-profit AI research institute |
| 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 | AI2Bot-DeepResearchEval |
| Operator documentation | None published |
Ai2Bot-DeepResearchEval is operated by Ai2, a non-profit AI research institute. It's used to collect and scan resources used in deep research queries performed by Ai2's o…
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: AI2Bot-DeepResearchEval
Disallow: /User-agent: AI2Bot-DeepResearchEval
Allow: /User-agent: AI2Bot-DeepResearchEval
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking AI2Bot-DeepResearchEval 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
AI2Bot-DeepResearchEval is a bot operated by Ai2, a non-profit AI research institute that fetches single pages on demand for an AI assistant. Ai2Bot-DeepResearchEval is operated by Ai2, a non-profit AI research institute. 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 AI2Bot-DeepResearchEval 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 AI2Bot-DeepResearchEval 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 AI2Bot-DeepResearchEval 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.