Control Agent-to-Tool Interactions with Policy in Amazon Bedrock AgentCore | AWS Show and Tell

In this episode of "AWS Show and Tell – Trust your agent with Policy in Amazon Bedrock AgentCore", we explore how Policies in Amazon Bedrock AgentCore gives you deterministic, auditable control over your agent's behavior, enforced at the gateway before any tool call is ever executed. Through a real-world use case, you'll walk through the full policy lifecycle: authoring policies in Cedar using natural language, attaching them to your AgentCore Gateway, and watching live traffic evaluated in real time — transparently, instantly, and without relying on an LLM to decide what's allowed. By the end, you'll know how to stop hoping your agent behaves and start knowing it will. Helpful Links: 1. Product Documentation: https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy.html 2. Blogpost: https://aws.amazon.com/blogs/aws/amazon-bedrock-agentcore-adds-quality-evaluations-and-policy-controls-for-deploying-trusted-ai-agents/ 3. Code Samples: https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials/08-AgentCore-policy 4. Workshop: - Getting Started: https://catalog.workshops.aws/agentcore-getting-started/en-US - Deep Dive: https://catalog.workshops.aws/agentcore-deep-dive/en-US 5. Deep Dive discussion: https://www.youtube.com/watch?v=ymwpOYMg1ng&t=6s&pp=ygUfa2VlcCB5b3VyIGFnZW50cyBvdXQgb2YgdHJvdWJsZdIHCQmiCgGHKiGM7w%3D%3D