The AWS Developers Podcast

In this episode, we sit down with Shridhar Pandey, Principal Product Manager on AWS Serverless Compute, to explore how the serverless team is pioneering agent-native development. Shridhar walks us through a remarkable March 2026 where the team shipped three major capabilities in just three weeks — a Kiro Power for Durable Functions, a Kiro Power for SAM, and a serverless agent plugin now available in Claude Code and Cursor. We trace the journey from 18 months of traditional developer experience improvements — local testing, remote debugging, LocalStack integration — to the realization that AI agents are fundamentally changing how developers build, deploy, and operate serverless applications. The serverless MCP server, now approaching half a million downloads, laid the foundation, and the new agent plugin builds on it with four specialized skills covering Lambda functions, operational best practices, infrastructure as code with SAM and CDK, and durable functions. Shridhar shares his thinking on agent personas — developer agents, operator agents, and platform owner agents — and how the team is applying an 'AX' (agent experience) lens to every feature they ship. We also take a candid detour into how AI has transformed his own work as a product leader: research that took weeks now takes hours, document cycles that spanned days now wrap up in a single sitting, and a fleet of agents handles daily digests and data analysis for the team. Open source runs through everything — the MCP server, the plugin, the public Lambda roadmap on GitHub — and Shridhar invites the community to shape what comes next.With Shridhar Pandey, Principal Product Manager, AWS Serverless ComputeAWS Serverless MCP ServerAgent Plugins for AWS — GitHubIntroducing Agent Plugins for AWS — Blog PostAWS SAM Kiro Power AnnouncementAWS Lambda Public Roadmap — GitHubServerless Land — Patterns and ResourcesKiro PowersThe Innovator's Dilemma — Clayton ChristensenCompeting Against Luck — Clayton Christensen

Join us for a fascinating conversation with Alexander 'Sasha' Lisachenko (Software Architect) and Artem Gab (Senior Engineering Manager) from inDrive, one of the global leaders in mobility operating in 48 countries and processing over 8 million rides per day. Sasha and Artem take us through their four-year transformation journey from a monolithic bare-metal setup in a single data center to a fully cloud-native microservices architecture on AWS. They share the hard-earned lessons from their migration, including critical challenges with Redis cluster architecture, the discovery of single-threaded CPU bottlenecks, and how they solved hot key problems using Uber's H3 hexagon-based geospatial indexing. We dive deep into their migration from Redis to Valkey on ElastiCache, achieving 15-20% cost optimization and improved memory efficiency, and their innovative approach to auto-scaling ElastiCache clusters across multiple dimensions. Along the way, they reveal how TLS termination on master nodes created unexpected bottlenecks, how connection storms can cascade when Redis slows down, and why engine CPU utilization is the one metric you should never ignore. This is a story of resilience, technical problem-solving, and the reality of large-scale cloud transformations — complete with rollbacks, late-night incidents, and the eventual triumph of a fully elastic, geo-distributed platform serving riders and drivers across the globe.With Alexander Lisachenko, Software Architect, inDrive ; With Artem Gab, Senior Engineering Manager, Runtime Systems, inDriveRedis in Action — Josiah L. Carlson (Manning)AWS Well-Architected Framework — ElastiCache LensBrendan Gregg's Blog — Performance Analysis & ObservabilityUber H3 — Hexagonal Hierarchical Spatial IndexinDrive WebsiteAWS ElastiCache DocumentationValkey ProjectAWS Well-Architected Framework

It's a milestone — episode 200! And to mark the occasion, we're doing something we've never done before: hosting two guests at the same time. James Ward (Principal Developer Advocate at AWS) and Josh Long (Spring Developer Advocate at Broadcom, Java Champion, and host of 'A Bootiful Podcast') join Romain for a wide-ranging conversation about why Java and Spring AI are becoming the go-to stack for enterprise AI development. We kick off with Spring AI's rapid evolution — from its 1.0 GA release to the just-released 2.0.0-M3 milestone — and why it's far more than an LLM wrapper. James and Josh break down how Spring AI provides clean abstractions across 20+ models and vector stores, with type-safe, compile-time validation that prevents the kind of string-typo failures that plague dynamically typed AI code in production. The numbers back it up: an Azul study found that 62% of surveyed companies are building AI solutions on Java and the JVM. James and Josh explain why — enterprise teams need security, observability, and scalability baked in, not bolted on. We dive into the Agent Skills open standard from Anthropic and James's SkillsJars project for packaging and distributing agent skills via Maven Central. We also cover Spring AI's official Java MCP SDK (now at 1.0) and how MCP and Agent Skills complement each other for building capable, composable agents. The performance story is striking: Java MCP SDK benchmarks show 0.835ms latency versus Python's 26.45ms, 1.5M+ requests per second versus 280K, and 28% CPU utilization versus 94% — with even better numbers using GraalVM native images. Josh and James also walk us through Embabel, the new JVM-based agentic framework from Spring creator Rod Johnson, featuring goal-oriented and utility-based planners with type-safe workflow definitions built on Spring AI foundations. We close with a look at running Spring AI agents on AWS Bedrock AgentCore — memory, browser support, code interpreter, and serverless containers for agentic workloads.With James Ward, Principal Developer Advocate, AWS ; With Josh Long, Spring Developer Advocate, Broadcom — Java ChampionSpring AI DocumentationStart building with Spring — start.spring.ioSpring AI 2.0.0-M3 Release AnnouncementEmbabel — Agentic framework for the JVM by Rod JohnsonSkillsJars — Agent Skills via Maven CentralAgent Skills Open Standard (Anthropic)Amazon Bedrock AgentCoreCoffee + Software — Josh Long's YouTube channelA Bootiful Podcast — Josh LongJames Ward's blog and presentationsJosh Long's websiteDevNexus 2026 (Atlanta, March 4–6)Voxxed Days Zurich 2026 (March 24)

Linda Mohamed, AWS Community Hero and independent cloud consultant, went from Java telecom work to building serverless and multi-agent AI systems. She discusses discovering Lambda via an Alexa skill, creating Otto the multi-agent Slack bot, and turning an AI video-analysis pipeline into a paid product. Conversation covers conference-driven development, vibe coding versus spec-driven work, and practical choices for agent frameworks and deployment.

Michael Gasch, Product Manager for Lambda Durable Functions at AWS, walks through the evolution of serverless and the need for native orchestration. He discusses checkpoint-replay, wait patterns like callback and condition, LLM orchestration, ECS coordination, and when to pick Durable Functions versus other options. He also covers tooling wins, surprising customer feedback, and what’s coming next.

Mike Chambers, Senior Developer Advocate at AWS who builds agentic systems and open-source tooling. He unpacks OpenClaw’s rise and why local routing frameworks matter. He walks through async tool calling that keeps conversations flowing while long tasks run. He explores Strands Agents SDK, AI Functions as a new runtime idea, and what observability and trust mean for future agentic software.

Chris Miller, AI software engineer and AWS Hero since 2021, builds AI-assisted dev tools and multi-agent prototypes while organizing community events. He talks about multi-agent architectures and orchestration patterns. He recounts hackathon hacks, building animated AWS imposters, and practical deployment tradeoffs. He explores the Silicon Valley AI scene and realities of responsible, production-ready AI coding.

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.With Mike Chambers, Senior Developer Advocate, AWSMCP (Model Context Protocol)Strands Agents - Lightweight agent frameworkKiro IDE - AI-powered development environmentDeep Learning AI Conference (AI Dev 25)NeurIPS ConferenceAWS Developers YouTube Channel

Christian Banzolet, AWS Hero and Solution Architect at Bundesliga who builds serverless and AI-assisted developer tools. He walks through spec-driven versus vibe coding, how to write steering documents, and practical strategies for enterprise AI adoption. Topics include custom single-responsibility agents, context engineering, tool friction, and new serverless features like Durable Functions.

Sebastien Stormacq, Principal Developer Advocate and Swift specialist at AWS, shares his work on Swift for server-side use. He discusses Swift’s native compilation, memory safety without GC, modern concurrency, and why it fits serverless on AWS. Conversation highlights frameworks, tooling like Swift Bedrock, real-world migrations, and how teams can start building backend services with Swift.