Assistant fetchers
DuckAssistBot is a bot that fetches single pages on demand for an AI assistant, and its operator has not been publicly identified. DuckAssistBot is a web crawler that scans websites to collect content for DuckDuckGo's AI-assisted answers feature, which generates brief responses to search queries usin…. It honours robots.txt, and a request claiming to be DuckAssistBot can be checked against a published IP range file.
Request says
"DuckAssistBot"
Checked against
published IP ranges
Live check
Paste the address from the log line. It is checked against what the operator publishes.
Reference
| User agent | DuckAssistBotToken only: match on the substring. |
|---|---|
| Operator | Not publicly identified |
| Purpose | Assistant fetchers |
| Respects robots.txt | Honourssource |
| Verification method | IP rangesPublished IP range file DuckDuckGo documents the agent and the addresses it fetches from on its help pages. https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot/ |
| Crawl pattern | Not published |
| Robots.txt tokens | DuckAssistBot |
| Operator documentation | https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot/ |
DuckAssistBot is a web crawler that scans websites to collect content for DuckDuckGo's AI-assisted answers feature, which generates brief responses to search queries usin…
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: DuckAssistBot
Disallow: /User-agent: DuckAssistBot
Allow: /User-agent: DuckAssistBot
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking DuckAssistBot 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
DuckAssistBot is a bot that fetches single pages on demand for an AI assistant, and its operator has not been publicly identified. DuckAssistBot is a web crawler that scans websites to collect content for DuckDuckGo's AI-assisted answers feature, which generates brief responses to search queries usin…. It honours robots.txt, and a request claiming to be DuckAssistBot can be checked against a published IP range file.
Yes. The operator documents that DuckAssistBot reads robots.txt and follows Disallow rules for its own token. Rules take effect on the next fetch of the file, which can be hours or days after you publish them.
DuckDuckGo documents the agent and the addresses it fetches from on its help pages. The reference is published at https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot/.
Add the DuckAssistBot 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 DuckAssistBot 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.