This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
This course teaches learners how to propagate user authorization context through AI agents built with Amazon Bedrock AgentCore, ensuring each user sees only the data they are authorized to access. Using a CRM chat application as an example -- where Sales and Finance departments share the same agent but need isolated data access -- learners explore patterns for enforcing least privilege access across Amazon DynamoDB, Amazon Bedrock Knowledge Bases, and external platforms like Salesforce. The key takeaway is that access control should be enforced by infrastructure and downstream services, not by agent code, following AWS Well-Architected best practices.
