The AWS Developers Podcast

What happens when a data scientist builds a generative AI proof of concept — and it scales to 700,000 articles and 4 billion page views? Recorded live at AWS Summit London, Romain is joined by Lewis James, Senior Data Scientist at Reach PLC — the UK's largest commercial publisher with over 120 brands including the Mirror, the Express, and OK Magazine. Lewis shares the full journey from GPT-2 experiments to a production AI publishing platform called Launchpad that now assists with 20–30% of the portfolio's daily article output. We explore how the team earned journalist trust by focusing on mundane tasks first, how they built multi-model pipelines with quotation fidelity checks to avoid misquoting, and why working backwards from users — not pushing technology — drove adoption where others failed. The conversation covers the technical evolution from prompt engineering to fine-tuning, model distillation, and agentic workflows built with the Strands Agents SDK running on Amazon Bedrock AgentCore. Lewis also introduces the concept of 'vibe publishing' — giving journalists a chatbot interface with more creative freedom — and discusses how evaluation strategies differ when you're measuring editorial tonality versus factual accuracy. Whether you are building AI-assisted content pipelines, navigating enterprise AI adoption, or thinking about how to earn user trust for generative AI tools, this episode offers a rare look at what three years of production generative AI looks like at massive scale.

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.

Recorded live at AWS Summit London, Matheus Guimaraes — Senior Developer Advocate at AWS and microservices specialist with over 25 years in tech — joins Romain to explore how agentic AI is reshaping the way we think about distributed systems architecture. From Martin Fowler's 2014 definition to agentic microservices in 2026, Matheus unpacks why the same distributed systems patterns — single responsibility, context dilution, failure modes — keep resurfacing in every new wave of architecture. The conversation covers the monolith vs. microservices debate as a deliberate architectural choice rather than accidental spaghetti, modular monoliths with Spring Modulith, and how AI coding assistants like Kiro are changing the architect's role from writing boilerplate to making higher-order design decisions. Matheus introduces his concepts of 'smart APIs,' 'monolithic agentic microservices,' and 'specialized agentic microservices' — and explains his talk 'Is It Agent?' on when to reach for agents vs. traditional applications. We dig into the serverless primitives purpose-built for agentic workloads: Amazon Bedrock AgentCore Runtime for long-running agent processes, AWS Lambda Durable Functions for multi-step workflows, and the AWS DevOps Agent for autonomous incident response. We also explore integration patterns with MCP and Google's A2A protocol, the 'lost in the middle' problem with context dilution, and why critical thinking about AI adoption matters more than ever. Whether you are decomposing a monolith or designing your first agentic system, this conversation connects the dots between a decade of microservices wisdom and the agentic future.

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.

Simon Martinelli is a Java Champion, Vaadin Champion, and Oracle ACE Pro with over three decades of experience building enterprise software. In this episode, he introduces the AI Unified Process (AIUP) — a methodology he created that combines the rigor of the Rational Unified Process with modern AI-assisted development, and makes a compelling case for why specifications, not code, should be the source of truth. We explore the difference between system use cases and user stories, and why use cases — with their actors, preconditions, main flows, alternative flows, and business rules — give AI agents far better structure to generate working code. Simon walks through the four phases of AIUP: Inception, Elaboration, Construction, and Transition, showing how specs, code, and tests evolve together iteratively while staying in sync. On the architecture side, Simon advocates for Self-Contained Systems over microservices — vertical slices that include UI, backend, and database together, reducing cognitive load for both developers and AI agents. His tech stack of choice is Vaadin for full-stack Java UI, jOOQ for type-safe explicit SQL, and Spring Boot as the application framework — a combination he argues is uniquely well-suited for AI-driven development because it keeps everything in one language with no hidden behavior. We also dig into testing strategies with Karibu Testing for browserless Vaadin tests and Playwright for end-to-end coverage, how teams of two working on bounded contexts with trunk-based development are shipping faster than ever, and why the era of AI is bringing back the Renaissance developer — the generalist who understands the full stack from business requirements to production deployment.