AgentsSeptember 14, 2026via AWS Machine Learning Blog
Manage end-user OAuth consent for AI agents with Amazon Bedrock AgentCore
Why it matters
Enterprise agents need secure identity and authorization to act on user accounts. AWS is shipping the infrastructure to let agents request and manage OAuth consent at scale, removing a critical blocker for production agentic workflows.
Key signals
- Amazon Bedrock AgentCore Identity adds Consent portal
- Managed web experience and session binding endpoint for AgentCore Gateway
- Supports GitHub and Slack third-party OAuth (3LO) integrations
- Activity review and audit via AWS CloudTrail
- Addresses multi-tenant agent authorization patterns
- Amazon Bedrock AgentCore Identity adds Consent portal feature
- Managed web experience + session binding endpoint for AgentCore Gateway
- Supports 3LO (3-legged OAuth) integrations (GitHub, Slack mentioned)
- Activity tracking via AWS CloudTrail
- Targets end-user authorization workflows for autonomous agents
The hook
Amazon adds OAuth consent management to AgentCore — agents can now safely connect to third-party services on behalf of users.
Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and session binding endpoint for AgentCore Gateway. This post walks through provisioning a portal, configuring GitHub and Slack 3LO targets, and the end-user consent flow, and shows how to review activity in AWS …