El Bruno

⚠️ This blog post was created with the help of AI tools. Yes, I used a bit of magic from language models to organize my thoughts and automate the boring parts, but the geeky fun and the 🤖 in C# are 100% mine.

Hi!

Are you ready to dive into the world of AI agents? Join us for an exciting four-session live series at Microsoft Reactor where we’ll build OpenClawNet, a production-grade AI agent platform from scratch using .NET 10 and GitHub Copilot.

What You’ll Learn

Over four interactive sessions, we’ll transform a simple chatbot into an intelligent, autonomous agent capable of reasoning through complex tasks, calling tools, remembering context, and scaling to the cloud.

Here’s What We’re Building Together:

Session 1: Foundation & Local Chat (60 minutes) We kick off by scaffolding a complete .NET 10 solution with Aspire orchestration, Minimal APIs, SignalR for real-time communication, and a Blazor web UI. By the end, you’ll have a working local chatbot powered by Ollama or Foundry Local, complete with persistent chat history using SQLite and EF Core.

Session 2: Intelligence & Tools (60 minutes) Transform the chatbot into an agent that can actually do things. We’ll implement a tool framework with security guardrails, enabling your agent to access files, run commands, fetch web content, and schedule tasks. Watch as your agent reasons through multi-step problems autonomously.

Session 3: Skills & Memory (60 minutes) Personalize your agent with reusable skill bundles defined in Markdown. Add conversation memory and automatic summarization to manage token budgets. Your users will be able to toggle skills like “Git Expert” or “JavaScript Mentor” without touching a line of code.

Session 4: Production Ready (60 minutes) Take it to production with job scheduling, Azure OpenAI integration, Microsoft Foundry, monitoring dashboards, and comprehensive unit tests. Deploy to Azure Container Apps or run on-premises—your choice.

Why Join This Series?

🎯 Hands-On Learning: Every session includes working code you can follow along with, inspect, and extend

🤖 See Copilot in Action: Watch how GitHub Copilot accelerates real-world development

🏗️ Production-Grade Patterns: Learn architecture patterns you can apply immediately to your own projects

💬 Interactive & Live: Ask questions in real-time and engage with the community

🎥 Access Recordings: Can’t make it live? All sessions are recorded with supplementary guides

Who Should Attend?

This series is perfect for:

• .NET developers exploring AI capabilities
• Enterprise architects planning AI features for their applications
• GitHub Copilot enthusiasts who want to see it tackle complex, real-world scenarios
• Anyone curious about how modern AI agents actually work under the hood

Prerequisites

You’ll need intermediate C# and ASP.NET Core knowledge, the .NET 10 SDK, VS Code with GitHub Copilot (or Visual Studio), and Docker for local Ollama. An Azure subscription is optional for sessions 3-4, but everything works locally too.

The Technologies we’ll cover

• .NET 10 with Blazor, Minimal APIs, and SignalR
• Aspire for service orchestration
• Ollama and Foundry Local for local LLM inference
• Azure OpenAI and Microsoft Foundry for cloud-scale AI
• GitHub Copilot as your AI coding partner
• Microsoft Agent Framework to create and orchestrate agents
• EF Core with SQLite for data persistence

Let’s do this!

Join the series now and let’s build something awesome together!

👉 Register here: https://developer.microsoft.com/en-us/reactor/series/S-1652/

See you at Microsoft Reactor!