Sona

bedrockbot

AWS's crawler for Amazon Bedrock - fetches your site when Bedrock customers add it as a knowledge-base source for their AI apps.

Reference reviewed by Sona

OperatorAmazon (AWS)
PowersAmazon Bedrock knowledge-base crawls
PurposeUser-triggered fetch
User-agent tokenbedrockbot
Respects robots.txtYes

bedrockbot crawls URLs that Amazon Bedrock customers configure as web data sources for their knowledge bases - the retrieval layer behind custom RAG applications and enterprise assistants built on Bedrock.

AWS documents that the crawler always adheres to robots.txt, honoring Allow and Disallow directives. In practice its user-agent carries a per-crawler UUID suffix (bedrockbot_UUID), but robots.txt rules for the generic bedrockbot token apply.

Full user-agent string

bedrockbot (+https://docs.aws.amazon.com/bedrock/latest/userguide/webcrawl-data-source-connector.html)

Allow bedrockbot

Enterprises building AI assistants on AWS can ground them in your content - relevant when partners or customers build on Bedrock.

User-agent: bedrockbot
Allow: /

Block bedrockbot

You don't want third-party Bedrock applications ingesting your site.

User-agent: bedrockbot
Disallow: /

Can bedrockbot read your page right now?

Test any URL and see exactly what AI crawlers receive.

Check my site