.svg)
Amazon Bedrock AgentCore Evaluations is now generally available
Amazon Bedrock AgentCore Evaluations Generally Available
Amazon Bedrock AgentCore Evaluations is now generally available, providing automated quality assessment for AI agents. Evaluations enable developers to monitor agent quality through continuous evaluation of production traffic, validate changes through testing workflows, and measure agent performance against defined expectations.
Key Features
- Continuous monitoring of agent performance in production.
- Support for regression testing in CI/CD pipelines.
- 13 built-in evaluators for response quality, safety, task completion, and tool usage.
- Integration with Ground Truth for measuring performance against expectations.
- Custom evaluators using prompts, models, or custom logic in Python/JavaScript.
- Integration with AgentCore Observability for unified monitoring and alerts.
Available Regions
- US East (N. Virginia)
- US East (Ohio)
- US West (Oregon)
- Asia Pacific (Mumbai)
- Asia Pacific (Singapore)
- Asia Pacific (Sydney)
- Asia Pacific (Tokyo)
- Europe (Frankfurt)
- Europe (Ireland)
What to do
- Learn more through the documentation.
- Get started with the AgentCore Starter Toolkit.
Source: AWS release notes
If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.
