The AWS Developers Podcast

Jas Narula, a Product Manager on the AWS Step Functions team, shares exciting updates on local unit testing for AWS workflows. He introduces the enhanced Test State API, allowing developers to test workflows with greater accuracy. Key features include support for advanced states like Map and Parallel, along with improved mocking capabilities. Jas discusses collaboration with LocalStack for offline testing and how popular frameworks like PyTest and Jest can be integrated. This new approach transforms Step Functions development into a more traditional test-driven environment.

Roopal Jain, a Senior Software Development Engineer at AWS, discusses the Builder Center, a new hub for AWS developers that centralizes resources like articles and events. She shares insights on the architecture using serverless microservices and the integration of the Neptune graph database for social features. Roopal also dives into challenges like VPC networking and dual authentication methods while outlining the new Builder ID for streamlined user access. Listeners gain a glimpse of the future roadmap for consolidating more AWS community tools into this platform.

Olly Pomeroy, a Senior Specialist Solutions Architect for Containers at AWS, dives into Amazon ECS Managed Instances, blending EC2 flexibility with Fargate's management. He discusses the architecture behind managed instances and the use of BottleRocket OS for enhanced security. Listeners learn about instance lifecycle management, pricing models, and how AWS optimizes instance selection for cost efficiency. Olly also highlights industry trends in container usage and previews exciting upcoming announcements from ECS.

In this engaging discussion, Alex Huides, a Principal Network Specialist Solutions Architect at AWS, shares insights on simplifying networking for developers. He introduces Amazon VPC Lattice, which helps eliminate complex IP concerns and establishes seamless communication across different accounts and VPCs. Alex explains the innovative concept of service networks that allows developers to focus on application connectivity without getting bogged down by network intricacies. He also touches on trends in global connectivity and the future of application networking.

In this engaging discussion, Alexandra Huides, a Principal Network Specialist Solutions Architect at AWS, shares her vast expertise in cloud networking. She emphasizes why developers need to grasp networking fundamentals for troubleshooting and performance. The conversation dives into latency's impact on app design, the evolving roles between developers and network teams, and critical VPC concepts like Peering and Transit Gateway. Alexandra also introduces Amazon VPC Lattice, which aims to streamline collaboration between developers, networks, and security teams for better application connectivity.

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.With Abrom Douglas, Solution Architect, Amazon CognitoAgentCoreAgentCore IdentityAbrom's blog post about AgentCore IdentityAgentCore Identity sample code

Arron Bailiss, Principal Engineer and Tech Lead for Strands Agents at AWS, brings his expertise to the discussion on building AI agents with the open-source Strands SDK. He shares how Strands evolved from an internal tool to a developer-friendly solution. Listeners will discover the framework's unique model-driven approach, simplified multi-agent systems, and how it powers AWS services like Amazon Q Developer. Arron also reveals exciting roadmap plans, including TypeScript support and voice capabilities for future agent development.

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.With Richard Pearson, Head of Engineering, Moonpig ; With Alexis Lowe, Principal Engineer, MoonpigMoonpig

Update Oct 25.: After we recorded this episode (July 10th 2025), AWS launched Amazon Bedrock AgentCore (that went in preview on July 16th, 2025) and generally available since Oct. 13rd, 2025. AgentCore is the recommanded solution to deploy your MCP agents on AWS. We keep this episode available as a learning experience but deploying MCP on Lambda is not the recommanded architecture for your production workloads. In this episode, we dive deep into MCP (Model Context Protocol) servers on AWS Lambda. We explore what MCP is, how it enables AI systems to interact with tools through standardized protocols, and practical implementations on AWS Lambda. The discussion covers authentication mechanisms, deployment strategies, and the future potential of MCP servers as a marketplace for AI capabilities. Whether you're building AI-powered applications or interested in exposing your business capabilities to AI systems, this episode provides valuable insights into the technical aspects and business opportunities of MCP servers.With Alexis Philippart de Foy, Solution Architect, AWSMCP Servers on Lambda, GitHub repoBuilding a Serverless remote MCP Server on AWS

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.With András Asbóth, Bioinformatician / Cloud Dev, Phagos ; With Andrea Di Gioacchino, Head of data, PhagosPhagosNextFlow