Home icon

Observing Agentic AI workloads using Amazon CloudWatch

AWS Cloud Operations Blog



This article discusses how to observe and monitor agentic AI workloads using Amazon CloudWatch, focusing on a sample Weather Forecaster application built with Strands Agents SDK.

  • The solution demonstrates observability using three key pillars: metrics, traces, and logs
  • Uses OpenTelemetry standard to track key metrics like token usage, performance, and tool usage
  • Leverages Amazon CloudWatch and AWS X-Ray to collect and analyze telemetry data
  • Provides step-by-step guidance on deploying the application and analyzing telemetry in CloudWatch
  • Highlights the ability to view traces, perform transaction searches, and monitor application metrics

The key takeaway is that comprehensive observability is crucial for agentic AI applications, and CloudWatch provides powerful tools to monitor and analyze their performance and behavior.



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

Jun 22
2026
Architecting distributed agentic AI workloads across AWS hybrid cloud services
May 26
2026
AgentWatch: Proactive AWS monitoring with ambient agents
Mar 13
2025
Part 1: Introduction to observing machine learning workloads on Amazon EKS
Apr 15
2026
Rede Mater Dei de Saúde: Monitoring AI agents in the revenue cycle with 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.