Building Intelligent .NET Applications: From AI Features to Agentic System

AI is becoming a core part of modern application development, and .NET offers a practical, incremental way to get started. In this session, you'll learn how to build intelligent .NET applications by adding useful AI capabilities—well beyond the chatbot—using Microsoft.Extensions.AI and .NET’s unified AI abstractions. We'll start with the essentials: integrating large language models, adding features like summarization, classification, and semantic search, and working with both cloud-hosted and local models in a maintainable, production-ready way. You'll see concrete patterns for introducing AI into existing applications with minimal friction. You'll also learn how to ensure quality and governance as you integrate AI into your enterprise. From there, we'll look at how these same foundations scale into more advanced, agentic solutions. You'll get an introduction to agentic development and see how the Microsoft Agent Framework enables applications to reason, plan, and take action using tools and workflows. Whether you're just beginning with AI in .NET or preparing for more autonomous, agent-driven systems, this session provides a clear roadmap from practical AI features to agentic architectures. Connect with .NET: Blog: https://aka.ms/dotnet/blog Twitter: https://aka.ms/dotnet/twitter TikTok: https://aka.ms/dotnet/tiktok Mastodon: https://aka.ms/dotnet/mastodon LinkedIn: https://aka.ms/dotnet/linkedin Facebook: https://aka.ms/dotnet/facebook Docs: https://learn.microsoft.com/dotnet Forums: https://aka.ms/dotnet/forums 🙋‍♀️Q&A: https://aka.ms/dotnet-qa 👨‍🎓Microsoft Learn: https://aka.ms/learndotnet #dotnet

Everything You Need to Know About the Latest in C#

Union types are coming to C#! Unions model closed sets of data shapes, as commonly seen in e.g. wire protocols. Mads and Dustin explore the clean expression of intent and the confidence and elegance that unions lend to consuming code. We'll also take a look at other recent and upcoming C# features, such as extension members and closed classes. You will learn: Find out what's coming to the next version of C# How to express closed sets of types with unions How to add new members to existing types with extension members Connect with .NET: Blog: https://aka.ms/dotnet/blog Twitter: https://aka.ms/dotnet/twitter TikTok: https://aka.ms/dotnet/tiktok Mastodon: https://aka.ms/dotnet/mastodon LinkedIn: https://aka.ms/dotnet/linkedin Facebook: https://aka.ms/dotnet/facebook Docs: https://learn.microsoft.com/dotnet Forums: https://aka.ms/dotnet/forums 🙋‍♀️Q&A: https://aka.ms/dotnet-qa 👨‍🎓Microsoft Learn: https://aka.ms/learndotnet #dotnet

Claude Code: 5 reasons to run clear or compact

.NET AI Community Standup: MCP C# SDK 2.0: Building the Next Generation of .NET AI Agents

Join Bruno, Pranav, and Tarek for the next .NET + AI Community Standup. We’ll explore version 2.0 of the official MCP C# SDK, including its stateless-first design, standardized HTTP support, Multi Round-Trip Requests, and backward compatibility. We’ll also do an overview of Microsoft Foundry Hosted Agents and discuss how .NET developers can use these technologies to create scalable, interactive AI solutions. Expect expert insights, practical examples, and plenty of conversation for both experienced enterprise developers and those beginning their AI journey with .NET. 🔗 Links: https://learn.microsoft.com/en-us/collections/3gm2s6tekowkgk? 🎙️ Featuring: Bruno Capuano, Pranav Senthilnathan, Tarek Mahmoud Sayed #dotNET #AI #MCP

ASP.NET Community Standup: What's new in .NET 11 Preview 7?

Join the ASP.NET Core team for a tour of what's new for ASP.NET Core and Blazor in .NET 11 Preview 7: Output caching for Blazor, QuickGrid virtualization improvements, auto-pausing Blazor Server circuits, and much more! 🔗 Links: https://www.theurlist.com/aspnet-standup-20260811 🎙️ Featuring: Daniel Roth and Javier Calvarro Nelson, Daria Tiurina #dotnet #aspnetcore #blazor

PeerLLM Skills: Build, Test & Optimize Agent Skills Across Any LLM

Building skills for AI agents is hard because no two LLMs interpret the same skill the same way. A skill that works on GPT might fall apart on Mistral, Qwen, or Phi, leaving you to rewrite the same thing over and over. PeerLLM Skills solves this. It is a fully decentralized skills management portal, built on top of the PeerLLM network, that lets you build, test, evaluate, and fine-tune agent skills against any model, all from one place. In this demo I walk through: 0/ Building skills with blocks using an RFC 2119 structure (must, must not, may) instead of writing everything by hand. 1/ Multi-model evaluation that runs a single skill against Luma, Qwen, Mistral, Phi, GPT and more, with a compatibility score for each. 2/ One-click optimization, where one model improves a skill so it runs reliably on another, cheaper model. 3/ The decentralized network, where you can watch skills get tested live across distributed compute. 4/ Ratings, verification badges, and the compatibility matrix, so you can see exactly where a skill works and where it does not. 5/ Leaderboards and model success rates to find the most reliable skills and models. 6/ The CLI, to search and pull skills straight into your repo or JS app, pin versions, and publish to GitHub or a native registry. The result: instead of paying for an expensive external model just because your skills only work there, you can fine-tune skills to run on far cheaper models, cutting cost while keeping your agents reliable. Try it at https://skills.peerllm.com get to know about PeerLLM Decentralized AI project here: https://www.peerllm.com Got questions or ideas? Drop a comment below, and if you found this useful, please like and subscribe. 00:00 The problem: skills don't transfer between LLMs 01:13 Introducing PeerLLM Skills and the PeerLLM network 02:14 Evaluating a skill across models (compatibility scores) 02:38 One-click optimization: tuning a skill for another model 03:29 Touring the website at skills.peerllm.com 03:47 Browsing and downloading published skills 04:09 Skill details: runs, ratings, and contributing 04:41 Verification badges and the compatibility matrix 05:14 Cutting cost by running on cheaper models 05:43 Building a new skill from scratch with blocks 07:00 Testing your skill in real time on Luma and Qwen 07:42 Viewing skills as Markdown, adding tools and parameters 08:27 Generating goals and running them across the network 09:40 Resetting skills, schemas, comparing, and leaderboards 10:45 Using the CLI to search and pull skills 12:26 The block schema and RFC 2119 standard 13:06 Publishing skills to GitHub or a native registry 13:26 Wrap-up

.NET MAUI Community Standup: Inspect, Record, Create: .NET MAUI Meets GitHub Copilot Canvas 🤝

Join us with Dominik Titl for a look at a new developer tool that brings inspection, layout analyzers, test recording, and GitHub Copilot Canvas together for .NET MAUI. See how developers and Copilot can inspect and interact with running apps, create repeatable tests from those interactions, and use captured evidence to diagnose failures, all through a shared experience in Visual Studio Code, GitHub Copilot Canvas, or any modern browser. 🎙️ Featuring: David Ortinau (@davidortinau), Gerald Versluis (@jfversluis), Dominik Titl (@morning4coffe) 🔗 Links: https://www.theurlist.com/maui-standup-september26 #dotnetmaui #copilot #canvas

.NET Data Community Standup: You won't believe what Chris is doing with EF interceptors 🤯

Join us for another show where Chris Klug shows us all the things he uses interceptors for! 🎙️ Featuring: Chris Klug, Jiri Cincura #ef #efcore #data #dotnet #interceptors

Claude Code: what happens when you run /compact?