Build Strands Agents with SageMaker AI models and MLflow

Amazon AWS AI Blog / 4/28/2026

💬 OpinionDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The post shows how to build AI agents using the Strands Agents SDK while leveraging foundation models deployed on Amazon SageMaker AI endpoints.
It walks through deploying foundation models from SageMaker JumpStart and integrating them into Strands Agents for agent-based workflows.
It explains how to add production-grade observability by using SageMaker Serverless MLflow for agent tracing.
It covers running A/B tests across multiple model variants and evaluating agent performance using MLflow metrics.
The approach emphasizes building, deploying, and continuously improving AI agents on infrastructure the team controls.

In this post, we demonstrate how to build AI agents using Strands Agents SDK with models deployed on SageMaker AI endpoints. You will learn how to deploy foundation models from SageMaker JumpStart, integrate them with Strands Agents, and establish production-grade observability using SageMaker Serverless MLflow for agent tracing. We also cover how to implement A/B testing across multiple model variants and evaluate agent performance using MLflow metrics and show how you can build, deploy, and continuously improve AI agents on infrastructure you control.