This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
This hands-on course guides you through the complete lifecycle of building, containerizing, and deploying AI agents on Amazon Bedrock AgentCore Runtime. You will start by creating agents locally using the Strands SDK, then package them into production-ready containers, and finally deploy them as scalable, discoverable services on AWS.
The course covers the Strands SDK’s tool-first architecture, Docker containerization for AgentCore’s ARM64 requirements, the AgentCore HTTP contract (ports, endpoints, health checks), and deployment via CLI and Boto3. You will also learn how to expose your agent’s capabilities through MCP endpoints for tool consumers and A2A endpoints for peer agent discovery and collaboration.
By the end of the course, you will have deployed a multi-agent orchestration system where a supervisor agent delegates tasks to specialized agents — all running on AgentCore Runtime with full observability via CloudWatch and OpenTelemetry.
