Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore how to build trustworthy AI agents through Amazon Bedrock AgentCore's comprehensive safety and governance framework in this 36-minute conference talk from AWS re:Invent 2025. Discover fine-grained policy enforcement mechanisms that prevent unauthorized actions and protect sensitive data through identity-aware authorization and runtime isolation capabilities. Learn about millisecond-latency policy controls and built-in observability features that secure agent-to-tool interactions while maintaining performance. Examine practical architectural patterns for integrating safety, governance, and compliance as native components of your agent systems, ensuring your AI agents consistently operate within defined boundaries and organizational policies. Gain insights into implementing robust security measures that enable AI agents to handle complex real-world tasks responsibly while maintaining the agility and innovation potential of your cloud-based applications.
