GitHub Spec Kit with Den Delimarsky

How do you build quality software with LLMs? Carl and Richard talk to Den Delimarsky about the GitHub Spec Kit, which uses specifications to help LLMs generate code for you. Den discusses the iterative process of refining specifications to produce better code, and then being able to add your own code without disrupting the process. The conversation delves into this new style of software development, utilizing specifications to break down tasks sufficiently for LLMs to be successful, and explores the limitations that exist today.

The next version of CSLA is out! Carl and Richard talk to Rocky Lhotka about his business objects framework that pre-dates .NET itself! Rocky discusses the surge in development that occurred for version 9, where a company heavily dependent on CSLA contracted developers to clear some of the backlog. The result is a few new long-term contributors, resulting in an increased development candence and a substantial modernization of the code base. The conversation also turns to AI and its role in development, as well as Rocky's experiments with making an MCP server for CSLA!

Aspire has been around for almost two years. How do you use it effectively? Carl and Richard talk to Chris Klug about his experience with .NET Aspire. Chris discusses thinking cloud natively, whether you are going to the cloud or not - it's not just a place, but also an architecture. The conversation digs into the role of containers and Kubernetes, deployment strategies, telemetry, security, testing, and more. You can use as much or as little Aspire as you wish!

You write tests - but are they valuable tests? Carl and Richard talk to Egil Hansen about his approach to creating tests for applications. Egil discusses the types of testing and who they impact. Testing isn't only for you! Valuable tests are also durable, being able to persist between changes where it makes sense, and help to understand when updates are going to create problems. The role of LLMs in generating code comes into play: should AI write your tests, evaluate them, or do both? Lots of great thinking from someone who's been helping developers build better tests for years!

AI in the cloud dominates, but what can you run locally? Carl and Richard speak with Joe Finney about his work in setting up local machine learning models. Joe discusses the non-LLM aspects of machine learning, including the vast array of models available at sites like Hugging Face. These models can help with image recognition, OCR, classifiers, and much more. Local LLMs are also a possibility, but the hardware requirements become more significant - a balance must be found between cost, security, and productivity!

How has AI changed coding with Visual Studio Code? Carl and Richard talk to James Montemagno about his experiences using the various LLM models available today with Visual Studio Code to build applications. James talks about the differences in approaches between Visual Studio and Visual Studio Code when it comes to AI tooling, and how those tools continue to evolve. The conversation also digs into how different people use AI tools to answer questions about errors, generate code, and manage projects. There's no one right way - you can experiment for yourself to get more done in less time!

Razor Tooling is evolving! Carl and Richard talk to David Wengier about the changes coming for Razor Pages in the next version of Visual Studio. David talks about the realization that much of the new work in Razor ties closely to Roslyn, which has resulted in a new co-hosting model that means higher performance and reliability for your web pages! The conversation delves into how capabilities in Visual Studio Code are shared with Visual Studio and vice versa, as well as the role of the Language Service Protocol in making it easier to bring more powerful tools to you.

Ready for the next version of Visual Studio? Carl and Richard talk to Mads Kristensen about the long-awaited version of Visual Studio. Needless to say, artificial intelligence sits front and center. Mads talks about the deep integration of AI across the development lifecycle, including code completion, debugging, even natural language querying. The conversation also digs into the role of Visual Studio as a project management tool, and its integration with cloud, GitHub, and more!

How has DevOps changed in 2025? Carl and Richard talk to Michael Levan about his experiences helping teams automate their development workflows, and dealing with all the details that help the entire team focus on providing customer value. Michael digs into the role of the new AI tools in facilitating better workflows around code, testing, deployment, telemetry, and more. Then the conversation turns to security - and the many challenges that exist to make applications that are secure when deployed, and help with the security challenges that happen while in operation!

How did the design of GitHub evolve? Carl and Richard speak with Diana Mounter about her experiences at GitHub, including her role as head of design. Diana discusses how she was drawn to GitHub as a designer and how her career evolved to lead design for the company. The conversation ranges over different design concepts, the Primer design language, and how to effectively combine design and development to achieve great results.