DuckAssistBot — DuckDuckGo's ai search indexer

DuckAssistBot fetches source pages at answer time for summarization with citation links, drawing heavily on reference-quality sources.

Its volume is modest compared to the majors, in line with DuckDuckGo's search share, and DuckDuckGo's privacy-first positioning extends to a clean, documented bot.

DuckAssistBot identifies itself with the following user-agent string:

Mozilla/5.0 (compatible; DuckAssistBot/1.0; +http://duckduckgo.com/duckassistbot)

Never trust the user-agent string alone. Scrapers routinely impersonate well-known crawlers to inherit their access. DuckDuckGo documents its bots on its help pages; DuckAssistBot identifies itself consistently and honors robots.txt.

Note that most AI crawlers and fetchers, DuckAssistBot included, do not execute JavaScript — so this traffic is invisible to GA4 and every script-based analytics tool. Server logs, CDN analytics, or a dedicated bot-analytics layer are the only places you will see it. For the full picture of measuring AI-driven visits, see our guide on how to track AI traffic.

To refuse DuckAssistBot access to your entire site, add this to your robots.txt:

User-agent: DuckAssistBot
Disallow: /

To restrict it from specific sections only (for example, premium content) while leaving the rest open:

User-agent: DuckAssistBot
Disallow: /premium/
Disallow: /members/

The case for blocking: There is little to gain from blocking a low-volume, citing, non-training fetcher — unless you are simply blocking all AI answer surfaces on principle.

The case for allowing or monetizing: The return is citations in front of DuckDuckGo's privacy-conscious audience. Small but clean visibility, at negligible crawl cost.