Stephen Toub: AI in .NET - Episode 344
04/07/25 • 37 min
Stephen Toub is a Partner Software Engineer at Microsoft. Stephen has been at Microsoft for almost 24 years and has done it all. If it has to do with .NET, he’s been in it. And today, he looks after all the .NET libraries making sure .NET continues to be the fastest platform on the planet. He ran the MSDN Magazine before it morphed into the docs and blogs of today. He was a leader in the concurrency and async and parallel programming developments, and now he’s turned his attention to pushing the AI envelope with .NET.
Topics of Discussion:
[4:37] Stephen morphed a few of his many interests into the role he has today.
[6:04] How moments like the push for parallel computing, the open-sourcing of .NET, cross-platform support, and performance goals shaped Steven’s current focus. [7:37] Steven highlights the two major AI tracks: (1) AI-augmented tools that improve developer productivity, and (2) building AI capabilities into applications themselves.
[10:37] The future of user interfaces.
[12:43] Why “agents” are basically advanced actor-based systems empowered by large language models and tool calling, enabling reasoning and orchestration beyond simple Q&A. [23:22] Model context protocol.
[24:08] A paradigm shift in system integration.
[30:24] How Stephen and the .NET libraries team factor out common AI abstractions for the ecosystem, so that different frameworks (Semantic Kernel, Onnx Runtime, Olama, etc.) can interoperate.
[32:15] Steven gives examples of how minimal C# code, combined with locally hosted LLMs or cloud endpoints, can solve real tasks.
Mentioned in this Episode:
Programming with Palermo — New Video Podcast! Email us at [email protected].
Clear Measure, Inc. (Sponsor)
.NET DevOps for Azure: A Developer’s Guide to DevOps Architecture the Right Way, by Jeffrey Palermo
Demystifying Retrieval Augmented Generation with .NET
Want to Learn More?
Visit AzureDevOps.Show for show notes and additional episodes.
Stephen Toub is a Partner Software Engineer at Microsoft. Stephen has been at Microsoft for almost 24 years and has done it all. If it has to do with .NET, he’s been in it. And today, he looks after all the .NET libraries making sure .NET continues to be the fastest platform on the planet. He ran the MSDN Magazine before it morphed into the docs and blogs of today. He was a leader in the concurrency and async and parallel programming developments, and now he’s turned his attention to pushing the AI envelope with .NET.
Topics of Discussion:
[4:37] Stephen morphed a few of his many interests into the role he has today.
[6:04] How moments like the push for parallel computing, the open-sourcing of .NET, cross-platform support, and performance goals shaped Steven’s current focus. [7:37] Steven highlights the two major AI tracks: (1) AI-augmented tools that improve developer productivity, and (2) building AI capabilities into applications themselves.
[10:37] The future of user interfaces.
[12:43] Why “agents” are basically advanced actor-based systems empowered by large language models and tool calling, enabling reasoning and orchestration beyond simple Q&A. [23:22] Model context protocol.
[24:08] A paradigm shift in system integration.
[30:24] How Stephen and the .NET libraries team factor out common AI abstractions for the ecosystem, so that different frameworks (Semantic Kernel, Onnx Runtime, Olama, etc.) can interoperate.
[32:15] Steven gives examples of how minimal C# code, combined with locally hosted LLMs or cloud endpoints, can solve real tasks.
Mentioned in this Episode:
Programming with Palermo — New Video Podcast! Email us at [email protected].
Clear Measure, Inc. (Sponsor)
.NET DevOps for Azure: A Developer’s Guide to DevOps Architecture the Right Way, by Jeffrey Palermo
Demystifying Retrieval Augmented Generation with .NET
Want to Learn More?
Visit AzureDevOps.Show for show notes and additional episodes.
Previous Episode
Bruno Capuano: AI Developer Training in .NET - Episode 343
Bruno Capuano is a Principal Cloud Advocate at Microsoft where he empowers teams to build AI solutions with Azure using programming languages like C#, Python, and C++. His approach is to solve complex problems with minimal effort, delivering simple and efficient solutions in today’s fast-paced AI landscape. Bruno has led innovation in teams at Avanade across Canada and Europe, transforming cutting-edge technologies into practical business solutions. He is passionate about working with teams, helping them grow, achieve high productivity, and foster collaborative, positive environments. As an international speaker, he advocates for making AI accessible to everyone, empowering teams and organizations to harness its transformative potential. Outside of tech, he is a runner, a lifelong learner, and always looking for his next challenge—whether it’s mastering new skills or tackling a marathon.
Topics of Discussion:
[5:08] Bruno explains how his passion for learning and community engagement led him to a role where he could dedicate himself to education and advocacy.
[7:17] Why data scientists and new AI tools often favor Python first, and how Bruno and his team work to ensure .NET developers also have immediate access to modern AI capabilities.
[10:31] The progression of getting developers into AI.
[11:20] Starting with familiar tools like Notepad.
[13:39] The “must have’s” for developers who want to start writing AI code.
[17:20] The benefit of GitHub models.
[23:47] Vector Databases & Retrieval-Augmented Generation (RAG).
[25:17] How vector databases store information using numerical representations and enable semantic search.
[31:25] Bruno highlights how AI “skills” or “functions” can call external APIs to fetch real-time data.
Mentioned in this Episode:
Programming with Palermo — New Video Podcast! Email us at [email protected].
Clear Measure, Inc. (Sponsor)
.NET DevOps for Azure: A Developer’s Guide to DevOps Architecture the Right Way, by Jeffrey Palermo
Want to Learn More?
Visit AzureDevOps.Show for show notes and additional episodes.
Next Episode
Jerry Nixon: .NET Aspire and Databases - Episode 345
Jerry Nixon is a Principal Program Manager on the SQL Server team focused on the Data API builder. He’s also a fanatic for #CSharp, #StarTrek, and Etymology. He also serves as a professor at Colorado Christian University.
Topics of Discussion:
[3:34] Why Jerry describes his life as a pearl necklace.
[5:15] Jerry recommends the book Never Eat Alone and the importance of community.
[6:01] How engineers and parenting are aligned.
[7:02] Jerry reflects on Microsoft’s history of evangelism, the rise of “opinionated” frameworks, and how .NET Aspire revives a form of proven prescriptive guidance. [9:35] Prescriptive guidance.
[12:03] The inevitable evolution of .NET Aspire and how it simplifies container-based development by handling orchestration behind the scenes.
[16:56] Paying more attention and awareness to the developer community.
[18:30] How GraphQL fits into the Data API Builder experience, giving developers flexibility without needing to write complex backends.
[21:40] Jerry talks about community feedback on Data API Builder and how real-world use cases help prioritize features and fix gaps in tooling.
[31:02] Jerry’s perspective on building container-based solutions.
[32:15] Data API Builder’s community involvement and upcoming features.
[36:15] Docker Desktop.
[38:58] The architectural concept of Data API Builder.
[44:42] C# coding conventions at Microsoft and the friendly battles over things like naming, underscores, and formatting styles across internal teams.
Mentioned in this Episode:
Programming with Palermo — New Video Podcast! Email us at [email protected].
Clear Measure, Inc. (Sponsor)
.NET DevOps for Azure: A Developer’s Guide to DevOps Architecture the Right Way, by Jeffrey Palermo
.Net Aspire and Data API builder with the Community
Data API builder for Azure Databases samples
Quickstart: Use Data API builder with SQL
Want to Learn More?
Visit AzureDevOps.Show for show notes and additional episodes.
If you like this episode you’ll love
Episode Comments
Generate a badge
Get a badge for your website that links back to this episode
<a href="https://goodpods.com/podcasts/azure-and-devops-podcast-389797/stephen-toub-ai-in-net-episode-344-89027989"> <img src="https://storage.googleapis.com/goodpods-images-bucket/badges/generic-badge-1.svg" alt="listen to stephen toub: ai in .net - episode 344 on goodpods" style="width: 225px" /> </a>
Copy