Agentic AI in .NET with Spencer Schneidenbach

How do you balance architecture and code? Carl and Richard talk to Steve Smith about various architectural strategies and the swing back-and-forth against over-designing architecture and getting code written. Steve talks about how architecture changes depending on the size and number of teams, how the latest tools can help with architectural choices, and the challenge of effective refactoring when things need to change. Lots of great conversation!

Open Source Maintainers are burning out or going commercial - how do we solve this? Carl and Richard chat with Rob Mensching about his work to create the open source maintenance fee through GitHub. Rob talks about the common problem of single maintainers getting buried under issues and demands of consumers for a project. Recognizing that most people cannot contribute to the project, a maintenance fee helps support the maintainer in a low friction way for everyone involved. Check out the links to get started!

How can a large language model help your organization answer government RFPs? Carl and Richard talk to Vishwas Lele about his startup pWin, as in proposal win. Vishwas talks about being a year into the startup and his deeper understanding of how AI technologies can augment skilled operators to produce better quality products in less time, including responding to RFPs. The conversation digs into tuning the LLM to focus on the data relevant to each section of the RFP so that the operator can interact with the tool and build better responses!

Can you integrate performant audio-video into your .NET application? Carl and Richard talk to Elias Puurunen about his work at Tractus Events, where he uses the NDI protocols to bring real-time audio and video streams into his C# application. Elias talks about the power of P/Invoke to access the underlying libraries for controlling video streams, including utilizing NVidia GPUs for extremely fast encoding and decoding. You could write this code in C++, but why?

Ready to build an agentic AI in .NET? Carl and Richard talk to Spencer Schneidenbach about his work using large language models to enhance customer interactions in healthcare. Spencer discusses using the LLMs to summarize customer conversations to identify topic areas, sentiment, and other concerns. He digs into how Microsoft's Semantic Kernel makes connecting an OpenAI model to your APIs easy, fetching information and creating a context for testing reliability and consistency with these models. Check out the links for some great tools to help make your AI apps with .NET!

How do you measure the quality of a large language model? Carl and Richard talk to Dr. Jodie Burchell about her work measuring large language models for accuracy, reliability, and consistency. Jodie talks about the variety of benchmarks that exist for LLMs and the problems they have. A broader conversation about quality digs into the idea that LLMs should be targeted to the particular topic area they are being used for - often, smaller is better! Building a good test suite for your LLM is challenging but can increase your confidence that the tool will work as expected.

What are JavaScript promises, and why do you want to make them? Carl and Richard talk to Martine Dowden about all the various async options available in Javascript today, including Callbacks, Promises, Async/Await, and even ReactiveJS! Martine digs into some of the more remarkable features available, including grouping sync calls together so code is only called when they all complete, or the race option where only one needs to complete, and everything else is thrown away. Lots of power is available in Javascript today. Have you taken advantage of it?

What's the latest with .NET Aspire? Carl and Richard talk to Rob Richardson about his experiences with .NET Aspire to help build great .NET cloud apps. Rob talks about all the goodness that comes out of the box with Aspire, including OpenTelemetry, containerization, good security practices, and the excellent dashboard. The discussion turns to the challenges of evolving .NET to be better in the cloud, retrofitting existing applications with Aspire, and all the container choices you have in front of you with these tools. There's more than one way to fall into the pit of success!

Seventeen years of Automapper! Carl and Richard talk to Jimmy Bogard about his latest version of Automapper - and the challenge of maintaining a long-lived and much-loved open-source library! Jimmy talks about the origins of Automapper as a tool he needed for working with clients and automating the mapping of objects. Initially, he moved to GitHub on Codeplex in 2009, and as open source became more popular in the .NET community, Automapper has hundreds of millions of downloads. And now, the next challenge - how to sustain this open-source project!

React version 19 has been released! Carl and Richard talk to Aurora Scharff about the long-awaited version of React that incorporates React Server Components and many other features. Aurora talks about the rethink involved in switching to a server-first implementation of a React website, which is best suited for greenfield implementations. For existing React apps, you'll want to look at React Router, which has V7, incorporates Remix features, and provides a bridge between React 18 and 19. Lots of progress from the library that runs Facebook!