The AWS Developers Podcast

AI agents are transforming how we write, test, and ship software — but are they actually improving the developer experience? Recorded live at AWS Summit London, Romain is joined by Tomasz Ptak — AWS AI Hero and Senior Engineer at Duco — for a candid conversation about developer experience friction in the age of AI agents. We explore what happens when teams adopt AI coding assistants without thinking about the developer workflow holistically — from context overload and broken feedback loops to the hidden costs of AI-generated code that nobody reviewed. The conversation draws on Werner Vogels' 'Renaissance Developer' keynote from re:Invent 2025, where he argued that developers need to be broader thinkers, not just faster coders. Tomasz shares his perspective on what great developer experience looks like when AI agents are part of the picture, how the AWS AI League is helping developers build real agent skills through gamified competition, and why critical thinking about AI adoption matters more than blind acceleration. We also discuss psychological safety in engineering teams — drawing on Brené Brown's work on vulnerability — and why the best developer tools are the ones you barely notice, as Don Norman taught us decades ago. Whether you are building AI agents, designing internal developer platforms, or evaluating how AI tools fit into your team's workflow, this conversation offers a grounded, human-centered perspective on reducing friction and improving developer experience in 2026 and beyond.

CyberArk's support team was drowning in logs. With 40+ products across SaaS and self-hosted environments, each generating logs in different formats, support engineers were spending days just preparing data before they could even start investigating a customer issue. Complex cases took up to 15 days to resolve. Moshiko Ben Abu, a Software Engineer at CyberArk — now part of Palo Alto Networks — built an AI-powered system that changed all of that. In this episode, he walks us through the full architecture: replacing manual regex parsers with AI-generated grok patterns using Amazon Bedrock and Claude, storing structured data in Apache Iceberg tables via PyIceberg with automatic schema evolution, and querying everything through Athena — all while keeping PII masked and data encrypted in S3. But the real breakthrough came with agents. Moshiko describes how he moved from single-product Bedrock agents to a swarm of specialized AI agents built with the Strands framework, where agents investigating product A can autonomously call agents for product B and C to trace root causes across the entire stack. Cases that took 15 days now resolve in hours. Simple cases drop from 4-6 hours to 15-30 minutes. Engineers handle 4x more cases per day. We also dig into the security layer — Cedar policies and Amazon Verified Permissions for agent authorization, the identity integration with AgentCore, and what's coming next: S3 Tables, AgentCore in production, and cross-platform agent collaboration with Palo Alto. Moshiko's advice for developers getting started? Learn IAM first, then compute, then databases — and write everything in CDK.

What if you could combine the creative power of generative AI with the mathematical certainty of formal verification? In this episode, Danilo Poccia — Principal Developer Advocate at AWS — breaks down automated reasoning, a field of AI that has been quietly powering critical AWS services for years and is now becoming essential for production AI systems. We explore why generative AI alone is not enough for high-stakes applications, and how automated reasoning provides mathematical proof — not probabilistic guesses — that your AI agents are following the rules. Danilo traces the roots of automated reasoning back to the 'symbolist' branch of AI, explains how AWS has used it internally for years to verify S3 bucket policies, encryption algorithms, and network configurations, and shows how it now converges with neural networks in what researchers call neurosymbolic AI. On the practical side, we dig into Amazon Bedrock Guardrails with Automated Reasoning checks — the first and only generative AI safeguard that uses formal logic to verify response accuracy. Danilo walks through how developers can use policy verification for agentic systems and tool access control with Cedar, and how AgentCore Gateway fits into the picture for managing MCP-based tool interactions at scale. We also cover the open source landscape: Dafny for verification-aware programming, Lean as a theorem prover, Prolog for logic programming, and the growing ecosystem of MCP servers that bring these capabilities into everyday development workflows. Whether you are building AI agents for production or just curious about what comes after prompt engineering, this conversation will change how you think about AI reliability.

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.

Some guests make you want to close your laptop and go build something. Linda Mohamed is one of them. In this episode, Romain sits down with Linda — AWS Community Hero, User Group Leader, Chairwoman of the AWS Community DACH Association, and independent cloud consultant based in Vienna. Linda started as a Java developer in on-premises enterprise environments. Her first AWS touch point? Building an Alexa skill for a smart home product — discovering Lambda almost by accident, and never looking back. Today she's building multi-agent AI systems, running an AI-powered video pipeline with five media customers, and doing it all while being one of the most energetic and generous contributors in the AWS community. Discover Linda's journey from Java developer in telecom to cloud and AI consultant, conference-driven development as a forcing function to ship, building Otto — a multi-agent Slack bot using Crew AI, LoRA fine-tuning, and Amazon Bedrock Agent Core Runtime. Learn about the AI-powered video analysis pipeline she built to solve her own problem and ended up selling to five media customers, vibe coding vs spec-driven development and when each makes sense, and why Clean Code principles still apply when designing agent architectures.

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.

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.

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.

In this episode, we dive deep into AWS Builder Center, the new community platform designed to consolidate all AWS developer resources into one central hub. Roopal Jain, Software Development Engineer on the Builder Center team, explains how this platform brings together previously scattered AWS community properties like re:Post, Skill Builder, and community.aws into a unified experience for builders. Beyond exploring what Builder Center offers - from articles and events to toolboxes organized by programming language - we take a technical deep dive into how the team built this large-scale web application. Rupal shares the architectural decisions behind their serverless microservices approach, the challenges of integrating Neptune graph database for social features like user following, and creative solutions for handling dual authentication methods in API Gateway. The conversation reveals real-world implementation challenges that many developers face, from VPC networking complexities to service-to-service authentication patterns. We also discuss Builder ID, AWS's new individual identity system, and get a glimpse of what's coming next for the platform.

In this follow-up episode of the AWS Developers Podcast, we continue the conversation with Alex Huides, Principal Network Specialist Solutions Architect at AWS, focusing on Amazon VPC Lattice. We explore how developers can simplify networking concerns while maintaining robust connectivity between applications. Alex explains how VPC Lattice introduces a new boundary concept called service networks, which allows applications to communicate across accounts and VPCs regardless of IP overlap issues. The discussion covers how VPC Lattice abstracts away complex networking details, replacing traditional load balancers while providing secure, private connectivity between services. This episode demonstrates how AWS is removing undifferentiated heavy lifting in networking, making it easier for developers to focus on building applications.

In this episode of the AWS Developers Podcast, we dive deep into Amazon Bedrock Agent Core Identity with Abram Douglas. Learn how this new service helps developers manage identities and authentication flows for AI agents at scale. Discover the seven core components of Agent Core and understand how the identity service simplifies complex OAuth2 flows and token management. Whether you're building AI agents that need to interact with third-party services like Google Calendar or Slack, this episode explains how Agent Core Identity removes the undifferentiated heavy lifting of identity management, token vaulting, and secure credential handling. Perfect for developers looking to deploy production-ready AI agents with enterprise-grade security.

In this episode, we dive deep into Moonpig's migration journey from an on-premise ASP.NET monolithic application to a fully serverless architecture on AWS. Richard Pearson, Head of Engineering, and Alexis Lowe, Principal Engineer at Moonpig, share their experience transforming a 25-year-old e-commerce platform. They discuss how they tackled the challenges of migrating from SQL Server to DynamoDB, implemented multi-region deployment, and achieved seamless scalability for their peak trading periods. Learn about their "no VPC" policy, their approach to observability, and how they organized their teams to embrace DevOps culture. This episode is particularly relevant for organizations considering a similar journey to serverless architecture or looking to scale their platforms globally.

In this episode, we explore how Phagos, a French biotech startup, combines biology, data science, and cloud computing to combat antimicrobial resistance. Their innovative approach uses bacteriophages - natural predators of bacteria - as an alternative to antibiotics. We discuss how they leverage AWS services, including SageMaker and batch processing, to analyze genomic data and train specialized language models that can predict phage-bacteria interactions. Our guests explain how they process terabytes of genetic data, train and deploy AI models, and create user-friendly interfaces for their lab scientists. This fascinating conversation reveals how cloud computing and artificial intelligence are revolutionizing biotechnology and potentially helping solve one of this century's biggest health challenges.