Home icon

Amazon Bedrock AgentCore adds quality evaluations and policy controls for deploying trusted AI agents

AWS News Blog

This article announces new capabilities in Amazon Bedrock AgentCore to enable secure, trusted AI agent deployment at scale.

  • Policy in AgentCore (Preview) – Define agent action boundaries using natural language or Cedar policy language
  • AgentCore Evaluations (Preview) – Monitor agent quality with built-in and custom evaluators for correctness, helpfulness, safety
  • Episodic Memory – Agents learn from past experiences and adapt solutions for improved consistency
  • Bidirectional Streaming – Voice agents listen and respond simultaneously for natural conversations
  • AgentCore SDK downloaded 2 million times in 5 months since preview launch
  • Available in multiple AWS regions with pay-as-you-go pricing and free tier access

These features help organizations deploy agents confidently by balancing autonomy with necessary guardrails and quality monitoring.

Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Dec 2
2025
Amazon Bedrock AgentCore now includes Policy, Evaluations (preview) and more
Jul 16
2025
Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview)
Mar 31
2026
Build reliable AI agents with Amazon Bedrock AgentCore Evaluations
Mar 12
2026
Secure AI agents with Policy in Amazon Bedrock AgentCore

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.