---
schema_version: "newruntime-reader-dossiers-v1"
type: "reader_dossier"
slug: "duckassistbot"
kind: "ai_answer"
operator: "DuckDuckGo"
researched_at: "2026-10-23"
confidence: "high"
json_url: "https://newruntime.com/readers/duckassistbot.json"
canonical_url: "https://newruntime.com/readers/duckassistbot/"
---

# DuckAssistBot

> Crawls pages in real time to supply DuckDuckGo's AI-assisted answers (DuckAssist), which cite their sources. DuckDuckGo states the data is not used to train AI models.

## Dossier

- Kind: AI search & answer engines
- Operator: DuckDuckGo (https://duckduckgo.com/)
- Documentation: https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot
- robots.txt tokens: DuckAssistBot
- Feeds: live answer fetch
- Respects robots.txt: Yes, per its documentation. Opt-out via robots.txt takes effect after 72h; does not affect organic ranking.
- Verification: Published IP ranges (https://duckduckgo.com/duckassistbot.json)
- Labels matched in our logs: duckassistbot

## Why it matters to New Runtime (our interpretation)

A DuckAssistBot hit means a DuckDuckGo AI answer is being built from our page, with a citation back.

## Observed behaviour

- Baseline 2026-10-23 (93-day window): 6 requests on 4 days; first seen 2026-09-11, last seen 2026-10-21; Returning.
- Live numbers: https://newruntime.com/bot-traffic-history.json and https://newruntime.com/crawler-journeys.json

## Sources

- https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot
- https://duckduckgo.com/duckassistbot.json

Identity: A family name is what a client claims in its user agent. It is verified only when its request came from the operator's published IP ranges or passed forward-confirmed reverse DNS, as reported per family in /crawler-journeys.json. Anyone can claim any name.

All dossiers: https://newruntime.com/readers.md