Amazon CloudWatch GenAI observability now supports Amazon AgentCore Evaluations
News
This article announces Amazon CloudWatch's new GenAI observability feature for automated quality assessment of AI agents through AgentCore Evaluations.
- 13 pre-built evaluators assess helpfulness, tool selection, and response accuracy
- Supports custom model-based scoring systems for tailored evaluation
- Unified quality metrics and agent telemetry visible in CloudWatch dashboards
- End-to-end tracing correlates evaluation metrics with prompts and logs
- Integrates with Application Signals, Alarms, Sensitive Data Protection, and Logs Insights
- Eliminates need for custom evaluation infrastructure development
- Available in US East, US West, Europe (Frankfurt), and Asia Pacific (Sydney)
CloudWatch GenAI observability now enables developers to continuously monitor and improve AI agent performance, identifying quality issues before customer impact.
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
Oct 13
2025
2025
Generative AI observability now generally available for Amazon CloudWatch
Jul 16
2025
2025
Amazon CloudWatch adds generative AI observability (Preview)
Nov 21
2025
2025
Amazon CloudWatch Introduces In-Console Agent Management on EC2
Dec 2
2025
2025
Amazon Bedrock AgentCore adds quality evaluations and policy controls for deploying trusted AI agents
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.