.NET Rocks!

Mark Seemann, a programmer with an economics background and blogger at blog.ploeh.dk, shares his insights on the impacts of AI, particularly large language models, on software development. He addresses the pitfalls of viewing AI as an ultimate source of truth and the essential knowledge required to evaluate AI-generated code. The conversation touches on the challenges faced by junior developers, the ethical implications of AI, and the importance of critical thinking in an era increasingly reliant on technology. Practical discussions around integrating AI tools highlight the need for careful oversight.

How do you build progressive web apps in 2025? Carl and Richard talk to Lemon about his experiences building all sorts of PWAs for customers and entertainment. Lemon discusses going beyond the icon in PWAs and leveraging more powerful features, including service workers. The conversation also digs into some of the crazy talks done over the years, as well as gaming from browsers and more!

Mark Miller, Chief Architect at Developer Express and a Microsoft MVP, joins the conversation on leveraging AI to enhance coding efficiency. He discusses the innovative features in CodeRush, emphasizing a voice-driven assistant that minimizes context-switching. The dialogue explores the evolution of AI tools and their transformative impact on productivity. Mark reflects on overcoming challenges in coding with AI, ensuring consistency, and optimizing workflows, while also touching on historical milestones in AI development.

Seth Juarez, a machine learning expert from Microsoft, dives deep into the world of agentic AI. He explains the Model Context Protocol (MCP) and how it allows AI agents to collaborate more effectively. The discussion highlights the challenges of managing these advanced tools and emphasizes the need for clear governance. Listeners will enjoy insights into the evolution of AI, including the balance needed when working with user instructions in AI outputs, and the importance of narrowing tasks for better performance in real-world applications.

Matt Steele, a Georgia Tech grad focused on AI, shares insights on Hair Match, an app helping women with textured hair find the best products. Gheida Omar, founder of Girls I Save, discusses Signverse, a revolutionary app offering real-time translation for multiple languages and sign language. Daniel Kim, a Stanford student, presents Argus, a wearable device enhancing independence for those with low vision through object detection and facial recognition. Together, they illustrate how technology can empower and transform lives.

Nicole Forsgren, a DevOps and developer productivity expert, joins the discussion to reshape how we think about development. She dives into her upcoming book on eliminating friction in software creation, highlighting the vital role of AI technologies alongside traditional DevOps practices. The conversation explores enhancing productivity through better workflows, the differences between brownfield and greenfield projects, and how AI integration influences developer dynamics. With insights from DORA, Forsgren emphasizes that refining tools and methods is crucial for successful projects.

What happens when AI comes to your web testing tool? While at Build, Carl and Richard talked to Debbie O'Brien about the latest features in Playwright, including Playwright MCP, the model control plane for Playwright capabilities. Debbie talks about using Playwright MCP to buy a table. Ask your LLM what tests should be written for your web page, and then ask it to write them. The potential of these tools is to make more tests in less time that are more resilient as versions of both the website and the testing tools change!

Scott Hunter, Vice President of Product for Azure Development Experience, dives into the revolutionary world of coding agents. He discusses how the new agent mode in Visual Studio Code enables Large Language Models to evaluate entire solutions, not just single files. Scott reveals how these agents can automatically assign GitHub issues, generate code, and even create pull requests. The conversation highlights the impact of AI in enhancing developer productivity, making coding more efficient and effective.

What if you could use ElasticSearch serverless? While at Build, Carl and Richard chatted with Ken Exner about the new announcements around Elastic providing serverless storage and search! Ken talks about paying for only the data you move and store with serverless, rather than needing to operate any infrastructure for Elastic. The conversation digs into the potential of Elastic in Azure AI Foundry to provide ultra-fast access to current company data for your LLM implementations. Elastic did vector databases before LLMs made them essential for RAG - and you can take advantage of it!

Chris Woodruff, a seasoned software developer and Microsoft MVP, dives into the fundamentals of networking in C#. He breaks down web sockets, gRPC, SignalR, and more, highlighting the various approaches developers can take. The conversation touches on the new QUIC standards in HTTP/3, promising to simplify networking. Chris emphasizes the importance of exploring options beyond defaults and offers insights into fault tolerance in networking. The lively discussion also reflects on the evolving landscape of technology and the personal experiences that shape their journeys.