In this episode of the AWS Developers Podcast, Sebastien Stormacq is joined by Giuseppe Battista and Kevin Shaffer-Morrison for a deep dive into Agentic AI and the Model Context Protocol (MCP). They explore how startups are rapidly adopting generative AI and the business and technical hurdles they encounter along the way. The conversation covers how AI agents are integrated into workflows, the role of orchestration technologies, and how tools enhance the planning capabilities of AI models. The trio unpacks the MCP framework and its potential to standardize communication between large language models and tools—drawing a compelling analogy to how USB transformed hardware interactions. They also discuss the complexities of tool orchestration, including resource management and security, and what the rise of ‘tool definition engineering’ means for the future. From integrating MCP with platforms like Amazon Bedrock to rethinking the role of software engineers, this episode looks at how AI is reshaping the foundations of modern software development.
--------
48:59
Behind the Scenes of AWS SDK Development
In this episode of the AWS Developers Podcast, we sit down with Trevor Rowe, Senior Manager of the AWS SDK team, for a deep dive into the evolution and inner workings of the AWS SDKs. We explore how the SDKs scale to support over 320+ AWS services, the importance of maintaining backward compatibility, and the role of developer experience in shaping the SDK design. Trevor explains how the team uses Smithy to automate code generation, ensuring consistency and efficiency across different programming languages. The conversation touches on the growing adoption of modular architecture, community contributions via GitHub, and the team's efforts to improve performance, define better schemas, and simplify migrations. Whether you're building cloud applications or maintaining complex integrations, this episode offers a behind-the-scenes look at how AWS builds and evolves its core developer tools.
--------
41:26
promptz.dev, a repository for your Amazon Q Developer prompts
In this episode of the AWS Developers Podcast, we welcome Christian Bonzelet to discuss the art of prompting in software development. Together, we explore how PromptZ.dev helps developers structure and share their prompts to maximize efficiency. Christian shares his insights from hands-on workshops, the challenges engineers face, and the importance of community feedback. The episode also delves into the technologies used to build the platform, including Amplify Gen2, DynamoDB, and Cognito, as well as its integration with Amazon Q. Finally, they discuss the impact of AI on developers' workflows and the future of PromptZ.dev.
--------
29:18
AWS Trust Center: a conversation with AWS's CISO.
In this episode, Chris Betz, Chief Information Security Officer (CISO) at AWS, introduces the Trust Center, a new essential resource for understanding security and trust in the cloud. He explains how AWS helps businesses navigate the challenges of compliance, data protection, and security best practices. Betz also shares practical advice for developers, enabling them to seamlessly integrate security into their projects and leverage the available tools. He highlights the key role of Nitro technology in optimizing security and emphasizes the importance of visibility in maintaining customer trust. A must-listen episode for anyone concerned with cloud security.
--------
32:11
Duolingo: continuous integration on Amazon EC2 Mac
In this episode of the AWS Developers Podcast, we explore how Duolingo—the app with 100 million monthly active users—optimized its CI/CD infrastructure to handle builds for 300 pull requests every week. Sharanya Viswanath and Murtaza Javaid explain how their platform engineering team reduced build times from 50 minutes to just 16 minutes by migrating to Amazon EC2 Mac and implementing advanced autoscaling and caching strategies. We also discuss the importance of modularization, macOS and Xcode version management, and automation with Fastlane to make the process more robust and efficient. An interesting discussion on the technical challenges and solutions put in place to ensure resilience and stability for iOS builds at scale.
México