[invisit](https://invisit.dev) · [Docs](https://invisit.dev/docs) · [llms.txt](https://invisit.dev/llms.txt) · [llms-full.txt](https://invisit.dev/llms-full.txt)

# DuckAssistBot

> DuckAssistBot is an AI assistant fetcher run by DuckDuckGo. It crawls pages in real time for DuckDuckGo's AI-assisted answers, which cite their sources. DuckDuckGo says the data is not used to train AI models.

- Operator: DuckDuckGo
- Kind: AI assistant fetcher
- robots.txt token: DuckAssistBot
- Follows robots.txt: yes
- Source: https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot (checked 2026-11-05)
- Page: https://invisit.dev/bots/duckassistbot

## What is DuckAssistBot?

It crawls pages in real time for DuckDuckGo's AI-assisted answers, which cite their sources. DuckDuckGo says the data is not used to train AI models.

Fetches a page because a person asked an assistant about it, right now. Operators often say robots.txt does not apply to these user-triggered fetches.

DuckDuckGo says an opt-out takes effect after 72 hours and does not affect organic search rankings.

- [DuckDuckGo’s documentation](https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot)

## DuckAssistBot user agent

DuckDuckGo documents this user agent for DuckAssistBot. Version numbers in it change over time, so match on the name, not the whole string.

```
DuckAssistBot/1.2; (+http://duckduckgo.com/duckassistbot.html)
```

## Should you block DuckAssistBot?

Usually allow it. Each fetch is a person asking about your page right now, which is close to a visit. Blocking it in robots.txt may not stop it, since operators often treat these fetches as the person’s own.

## How to block DuckAssistBot in robots.txt

Add a group for its token to robots.txt at the root of your site.

A bot follows only the group that names it, so it ignores your `User-agent: *` rules once it has a group of its own. Repeat any paths you also want kept from it there.

```
User-agent: DuckAssistBot
Disallow: /
```

- [Build a robots.txt for AI bots](https://invisit.dev/tools/robots-txt-generator)

## How to verify a request is really DuckAssistBot

Anyone can send any user agent, so the string alone proves nothing.

DuckDuckGo publishes the IP ranges DuckAssistBot crawls from. A request that claims to be DuckAssistBot from any other address is not DuckAssistBot.

- [DuckAssistBot IP ranges](https://duckduckgo.com/duckassistbot.json)

## See when DuckAssistBot reads your site

Bots don’t run JavaScript analytics, so a script tag never sees them. invisit records crawler reads on the server instead, through its server SDK or a Cloudflare Worker, and shows which bots read which pages, next to your visitors.

- [Track crawlers with invisit](https://invisit.dev/docs/server/sdk#crawler-reads)

## Common questions

### What is DuckAssistBot?

DuckAssistBot is an AI assistant fetcher run by DuckDuckGo. It crawls pages in real time for DuckDuckGo's AI-assisted answers, which cite their sources. DuckDuckGo says the data is not used to train AI models.

### Is DuckAssistBot safe to block?

Usually allow it. Each fetch is a person asking about your page right now, which is close to a visit. Blocking it in robots.txt may not stop it, since operators often treat these fetches as the person’s own.

### How do I block DuckAssistBot?

Add “User-agent: DuckAssistBot” followed by “Disallow: /” to your robots.txt.