# AWS explains how to evaluate AI agents with Amazon Bedrock AgentCore Evaluations

> Original title: The agent evaluation playbook: Built-in, DeepEval, and AutoEval on Amazon Bedrock AgentCore Evaluations

- Source: AWS Machine Learning Blog
- Published: 2026-11-10T22:35:03.000Z
- Bad Influence: https://badinfluence.news/items/hiaea7vuzwxe1y242q75tg4b4
- Original: https://aws.amazon.com/blogs/machine-learning/the-agent-evaluation-playbook-built-in-deepeval-and-autoeval-on-agentcore/

## Summary

AWS says teams should start with business outcomes, then map them to observable agent behaviors and evaluators at the trace or session level. The post covers built-in evaluators, DeepEval and AutoEval managed evaluators, and custom evaluators on Amazon Bedrock AgentCore Evaluations. Evaluators marked "needs ground truth" run only in batch evaluation, because live traffic has no reference answer or expected path.