.NET Rocks!

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.

Erwin van der Valk, Principal Engineer at Duende Software, dives into the complexities of securing browser-based frontends with ASP.NET Core backends. He discusses the Backend for Frontend (BFF) security framework, which streamlines API integration for diverse clients. The conversation highlights the importance of robust user authentication, handling OAuth 2.0 challenges, and managing tokens securely. Erwin also explores the nuances of Blazor rendering modes and the architectural advantages of multi-frontend support to boost development efficiency.

Steve Smith, an entrepreneur and software developer focused on quality software, joins the discussion about balancing architecture and coding. He addresses the fine line between over-design and getting work done, emphasizing how architectural strategies evolve with team size and tools. Steve shares insights on effective refactoring and the adaptability required in software development. The conversation also explores the role of modern tools, like GitHub Copilot, in fostering collaboration and reducing constraints on developers.

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!

Vishwas Lele, Co-founder and CEO of pWin and a Microsoft Regional Director, discusses how AI can revolutionize responding to government RFPs. He shares insights on tuning language models to enhance proposal quality and the importance of structured knowledge bases. The conversation highlights the balance between AI's rapid response capabilities and the need for human creativity and strategic thinking. Lele also emphasizes the significance of compliance and transparency in AI usage, ensuring that proposal responses meet stringent requirements.

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.