DuckAssistBot: getting cited in DuckDuckGo's AI answers

Operator

DuckDuckGo

Type

AI answer crawler

robots.txt token

DuckAssistBot

Follows robots.txt

Yes

Used for

Fetching pages in real time for DuckDuckGo's AI-assisted answers, which cite sources

User agent

User agent contains DuckAssistBot

How to verify

Compare the source IP with the addresses DuckDuckGo lists in its help pages

What is DuckAssistBot?

DuckDuckGo shows AI-assisted answers for some searches, with links to the sources used. DuckAssistBot is the agent that retrieves those source pages.

It is distinct from DuckDuckBot, DuckDuckGo's general search crawler. Blocking one does not block the other.

DuckDuckGo positions itself on privacy, and its AI-assisted answers follow the same idea: they are short, they appear only for some queries, and they point to the pages they summarise. That makes the format closer to a featured snippet with attribution than to a long chatbot reply, so pages that state a clear, self-contained answer near the top of a section are the ones most likely to be used.

What happens if you block DuckAssistBot?

Disallowing DuckAssistBot stops DuckDuckGo from using your pages in its AI-assisted answers. Your pages can still appear in regular DuckDuckGo results.

Should you allow DuckAssistBot?

Allow it. It is not a training crawler, and its answers cite sources, which is the kind of AI visibility that can send clicks from privacy-conscious users. If crawl load is a concern, disallow low-value URL patterns such as internal search results rather than blocking the agent outright, because a blocked page simply cannot be the source DuckDuckGo quotes.

Check whether DuckAssistBot can reach your site

Enter your domain or a specific page. The checker reads your live robots.txt, picks the group DuckAssistBot would use, and applies the longest matching rule, the same way major crawlers resolve conflicts.

robots.txt rules for DuckAssistBot

Put each group in the robots.txt file at the root of your domain. User agent names are matched without regard to case, and the most specific matching group wins.

User-agent: DuckAssistBot
Allow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: DuckAssistBot
Disallow: /account/
Disallow: /checkout/
Allow: /

The rule most people get wrong: once DuckAssistBot has its own group, it ignores everything under User-agent: *. If your wildcard group disallows paths such as /admin/, repeat those lines inside the DuckAssistBot group too.

How to verify real DuckAssistBot traffic

DuckDuckGo lists the IP addresses its bots use in its help pages. Compare the source address against that list before trusting the user agent.

To see how often it visits, count requests by user agent in your access log. On a typical Nginx server:

grep -i "DuckAssistBot" /var/log/nginx/access.log | awk '{print $4}' | cut -d: -f1 | sort | uniq -c

DuckAssistBot compared with similar agents

See all 20 agents side by side in the AI crawler directory.

DuckAssistBot FAQ

Abd Shanti

Co-founder and strategy lead at Outline Technologies, the team behind FreeGPTSEO and AI Citation Monitor. Abd works on how brands get found and cited by search engines and AI assistants.