aws-summits-reinvent-2025-serverless-agents-chalktalk
Building Production-Ready Agentic AI architectures with AWS Serverless
Agentic AI is transforming enterprise applications, but taking it from prototype to production requires more than just prompting. Join this chalk talk to discuss pragmatic, scalable patterns for building agentic AI systems using AWS Serverless services like Lambda, ECS Fargate, and API Gateway. You’ll learn how to architect and operate distributed agent-based systems, including patterns for running Model Context Protocol (MCP) servers. Together, we’ll walk through end-to-end architecture using the Strands Agents SDK, covering best practices for security, observability, and governance. Bring your questions — and leave with concrete patterns you can apply in your organization right away.
This repo contains resources referenced in:
- AWS Summit Toronto 2025 - SVS201 (slides)
- AWS Summit Los Angeles 2025 - SVS203 (slides)
- AWS re:Invent 2025 - CNS425 (TBD)
Resources
- Effectively building AI agents on AWS Serverless (blog)
- Building AI Agents on AWS with Strands Agents SDK (webinar, slides)
- Building MCP Servers on AWS (webinar, slides)
- Strands Agents SDK (docs)
- Amazon Bedrock AgentCore (preview)
- Sample MCP servers on AWS (github)
- E2E sample Travel Agent on Lambda (github)
- From authentication to identity propagation: Securing serverless AI agents and MCP servers on AWS with Okta (blog)
- Deploying serverless AI agents on AWS with Terraform and securing them with HCP Vault (blog)