Control where your AI agents can browse with Chrome enterprise policies on Amazon Bedrock AgentCore
Not a sandbox. AWS just shipped enterprise browser controls for AI agents—Chrome policies now enforce access restrictions on Bedrock AgentCore.
Why it matters
AWS is shipping production-grade governance features for agentic AI, addressing enterprise security requirements for autonomous browsing capabilities. This signals the shift from experimental agents to deployable, policy-controlled systems in regulated environments.
The key facts
10 to knowAmazon Bedrock AgentCore now supports Chrome enterprise policies for agent browser access control
Feature enables restriction of agents to specific websites
Includes session recording for policy enforcement observability
Custom root CA certificate support for enterprise security
Use case: agents researching documentation under enterprise browser restrictions
AWS Bedrock AgentCore adds Chrome enterprise policy integration
Enables browser agent restriction to specific websites
Supports custom root CA certificate validation
Session recording for policy enforcement visibility
Use case: controlled agent research within documented boundaries
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: In this post, you will configure Chrome enterprise policies to restrict a browser agent to a specific website, observe the policy enforcement through session recording, and demonstrate custom root CA certificates using a public test site. The walkthrough produces a working solution that researches…