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.

Strands Agents SDK is an open source SDK that takes a model-driven approach to building and running AI agents in only a few lines of code. Strands scales from simple to complex agent use cases, and from local development to deployment in production.

Amazon SageMaker JumpStart is a machine learning (ML) hub that can help you accelerate your ML journey. With SageMaker JumpStart, you can evaluate, compare, and select FMs quickly based on predefined quality and responsibility metrics to perform tasks, like article summarization and image generation.

SageMaker AI MLflow is a managed capability that streamlines the machine learning lifecycle through experiment tracking, model versioning, and deployment management.

A Jupyter notebook with complete code to use with this post can be found in the GitHub repo.