The AWS Developers Podcast

Mike Chambers is back — calling in from the other side of the globe — and he brought a lot to unpack. We pick up threads from our first conversation and follow them into genuinely exciting (and occasionally mind-bending) territory. We start with OpenClaw, the open-source agentic framework that took the developer world by storm. Mike shares his take on why it happened now — not just what it is — and why the timing was almost inevitable given how developers had been quietly experimenting with local agents for the past year. Then we go deep on asynchronous tool calling — a project Mike has been working on since mid-2024 that finally works reliably, thanks to more capable models. The idea: let your agent kick off a long-running task, keep the conversation going naturally, and have the result arrive without interrupting the flow. Mike walks through how he built this on top of Strands Agents SDK and why he's planning to propose it as a contribution to the open-source project. We also explore Strands Labs and its freshly released AI Functions — a genuinely new way to think about embedding generative capability directly into application code. Is this Software 3.1? Mike makes the case, and Romain pushes back in the best way. The episode closes with a look ahead: agent trust, observability with OpenTelemetry, and a thought experiment about what software might look like in five years if the execution environment itself becomes a model.

Join us for an engaging conversation with Chris Miller, an AWS Hero since 2021 and AI Software Engineer at Workato. Chris shares his journey from accidentally winning a DeepRacer competition to becoming a community leader in the San Francisco Bay Area. We dive deep into the realities of AI-assisted development, exploring multi-agent architectures, the Road to re:Invent hackathon experience, and what it's really like to be building in Silicon Valley's AI boom. Discover how Chris moved from DeepRacer champion to AWS Hero and community leader, his experience building a multi-agent imposter architecture featuring Jeff Barr, Swami, and Werner Vogels for the Road to re:Invent Hackathon, and the reality of moving beyond 'vibe coding' to responsible AI development. Learn about multi-agent orchestration patterns, token management, recursion limits, and the current state of AI development in San Francisco. Chris shares insights on developer tools like Kiro, the Strands framework, autonomous agents, and best practices for code review, testing, and transparency in AI-generated code. Whether you're exploring AI-assisted development, building multi-agent systems, or curious about the Silicon Valley AI scene, this conversation offers practical insights from the trenches.

Mike Chambers reflects on 2025 as 'the year of agents' - though not quite in the way he predicted. From MCP's rocky launch to the rise of AI coding assistants, Mike shares hard-won lessons about what actually worked in production, the security challenges developers face, and why the future might be about giving agents access to filesystems and command lines rather than endless tool definitions. Discover how MCP evolved from standard IO to becoming the plugin ecosystem for IDEs, the security concerns around giving agents local machine access, and context overloading challenges. Mike walks through the framework evolution from heavy prompt engineering to model-centric approaches, why he abandoned his own framework for Strands Agents, and the rise of lightweight frameworks like ADK, Strands, and Spring AI. Learn about the real agent success story of 2025: AI coding assistants like Kiro, and Claude Code expanding beyond just code. Mike shares insights on agent skills for progressive disclosure, giving agents filesystem and command line access, long-running multi-agent systems, and moving from laptop productivity to production-scale agents.

Christian, AWS Hero and Solution Architect at Bundesliga, shares his journey and hard-won lessons from adopting spec-driven development with AI coding assistants at enterprise scale. Learn when to use specs vs vibe coding, how to build effective steering documents, and practical strategies for helping engineering teams transition from traditional development to AI-assisted workflows. Discover the difference between spec-driven and vibe coding approaches, when to use each, and how to build effective steering documents that guide AI assistants. Christian shares enterprise adoption strategies that actually work, including the show-and-tell approach to reduce AI adoption fear, treating AI as a peer teammate, and creating centers of excellence for sharing learnings. We explore custom agents and the single responsibility principle, context engineering over prompt engineering, and dive into exciting re:Invent announcements like Lambda Durable Functions. Whether you're leading engineering teams, exploring AI-assisted development, or looking to optimize your development workflow, this conversation offers practical insights from real-world enterprise implementation.

Join us as we explore Swift beyond iOS with Sebastien Stormacq, AWS Developer Advocate and Swift specialist. Discover why Swift is becoming a compelling choice for server-side development, offering native compilation, memory safety without garbage collection, and modern concurrency features that deliver exceptional performance and cost efficiency. Seb shares how Apple processes billions of daily requests using Swift on AWS infrastructure, achieving 40% better performance and 30% lower costs when migrating services from Java. We dive into the technical advantages that make Swift competitive with traditional backend languages, explore the vibrant server-side ecosystem with frameworks like Vapor and Hummingbird, and discuss practical implementations including serverless architectures on AWS Lambda. Whether you're a Swift developer curious about server-side possibilities, a full-stack developer looking to unify your tech stack, or a backend engineer evaluating language options, this conversation offers practical insights into Swift's capabilities beyond the client.