DuckAssistBot

Operated by DuckDuckGoAI AssistantRespects robots.txt

Retrieves page content used to generate DuckAssist AI answers on DuckDuckGo.

What DuckAssistBot does

DuckAssistBot fetches pages to power DuckAssist, DuckDuckGo's AI-assisted answers. It retrieves source content that DuckAssist summarizes with attribution back to the source page.

Should I allow DuckAssistBot to crawl my site?

Allowing DuckAssistBot makes your pages eligible as cited sources in DuckAssist answers; blocking it removes you from that answer surface.

How to control DuckAssistBot

Target DuckAssistBot in your robots.txt with the DuckAssistBot token. Rules apply per bot, so you can allow this one while blocking others, or the reverse.

Allow DuckAssistBot

User-agent: DuckAssistBot
Allow: /

Block DuckAssistBot

User-agent: DuckAssistBot
Disallow: /

DuckAssistBot FAQ

What is DuckAssistBot?

DuckAssistBot is a DuckDuckGo crawler that crawls pages in real time to generate DuckAssist AI-assisted answers. DuckDuckGo states this data is not used in any way to train AI models.

How do I block DuckAssistBot?

Add a robots.txt group with "User-agent: DuckAssistBot" and "Disallow: /"; DuckDuckGo states the change takes effect after 72 hours. Opting out does not impact organic search rankings or whether your site appears in DuckDuckGo search results. The bot's IP addresses are published at https://duckduckgo.com/duckassistbot.json.

About AI Assistant Fetchers

Agents that fetch a page in real time because a user asked an AI assistant about it. They don't build an index; each visit maps to a live conversation.

Blocking these removes your pages from live AI answers at the exact moment a user is asking about you or your category.

See which bots visit your site

Temso helps marketers track every AI crawler and bot that visits your site, and runs regular audits to make sure your website is always performing at its full potential.

Explore Website Audits
Website audit dashboard showing bot visits, citation-bot visits, and a table of AI bots crawling the site