Creating a memory dump in C#
<p>Learn how to create a memory dump in C# to capture the state of your application for debugging purposes.</p> <p>The post <a href="https://devblogs.microsoft.com/dotnet/creating-a-memory-dump-in-csharp/">Creating a memory dump in C#</a> appeared first on <a href="https://devblogs.microsoft.com/dotnet">.NET Blog</a>.</p>
Experimental support for Device Bound Session Credentials (DBSC) in ASP.NET Core: Exploring the .NET 11 preview - Part 8
In this post I look at the new experimental support for DBSC provided by the Microsoft.AspNetCore.Authentication.DeviceBoundSessions package

Microsoft ignores C# and .NET... AGAIN
Another massive AI porting project at Microsoft decided to ignore C# and .NET and chose Rust... but why? And was it the right choice? 0:00 Intro 0:24 The Copilot Rust Migration 1:03 Community reaction 1:46 Architectural concerns 2:23 Rationale for choosing Rust 3:13 C# and native AOT capabilities 3:57 Performance and validity 4:23 AI generation and error analysis 5:33 Microsoft's broader rust adoption 6:47 Closing thoughts and critique #dotnet #csharp #rust
Spying on Claude Code: more lifecycle events, different blind spots
How Claude Code hooks differ from Cursor: broader lifecycle and permission telemetry, strong native IDs, batch and compaction events, but no thought or specialized execution hooks.

Is Local AI Worth it?
There's No Official Claude Agent SDK for C#. Here's What to Use Instead
The Claude Agent SDK (the package that turns Claude into an autonomous coding agent with tools, permissions, and a conversation loop) only ships officially for Python and TypeScript. In C#, the closest thing is buried inside the regular Anthropic SDK: a `ToolRunner` helper that drives the tool-use loop for you. Here's how to build a real file-editing, command-running agent with it, and where the unofficial alternatives fit.

.NET AI Community Standup: Interview Coach Evolves: MAF + GitHub Copilot SDK
We just updated the Interview Coach! Join Bruno Capuano and Justin Yoo to explore the latest evolution of Interview Coach, a .NET sample built with Microsoft Agent Framework (MAF), now with GitHub Copilot SDK support. Discover how Copilot moves beyond the code editor to power an application where specialist agents review resumes, ask behavioral and technical questions, and deliver personalized feedback. The Copilot SDK handles model interactions and tool calls, while Agent Framework coordinates the agents and their handoffs. With shared MCP tools, a Blazor interface, and continued Microsoft Foundry support, this sample offers a practical starting point for your own agent-powered applications. ๐ Explore the source code and continue learning with the companion walkthrough and hands-on workshop: https://aka.ms/mafinterviewcoach/repo https://aka.ms/mafinterviewcoach/blog https://aka.ms/mafinterviewcoach/workshop ๐ Links: https://learn.microsoft.com/en-us/collections/d4gkh1tee47wo?source=docs ๐๏ธ Featuring: Bruno Capuano https://www.linkedin.com/in/elbruno/, Justin Yoo https://www.linkedin.com/in/justinyoo/ #dotnet #MAF #GitHubCopilotSDK #Agents #AI

Scaling the Claw: Skills, Shell, CodeAct and Background Agents
Four additions make the agent genuinely useful. Skills package domain knowledge such as valuation and risk scoring into files it discovers and loads only when a request calls for them, including skills managed centrally in Foundry that update with no redeploy. Shell access lets it reorganise a messy folder of trade confirmations, confined to one working directory. CodeAct gives it a sandbox where it writes and runs code to work out an answer rather than guessing at the arithmetic. Background agents let it research several tickers at once and pull the results back together. ๐ This event is part of a series. Learn more here: https://aka.ms/FMTA/series ๐ Learn more by exploring the resource: https://aka.ms/AgentHarness #MicrosoftReactor #LearnConnectBuild [eventID:27519]

3 unknown Claude Code Skills #claudecode #claude #aiengineering
Build Your Own AI Agent Harness in C#, the MafClaw Live Series
<p>I am building a complete C# agent live, from a single call around an IChatClient to a production-ready, observable, governed agent, using the Microsoft Agent Framework harness in a 4-part Microsoft Reactor series.</p> <p>The post <a href="https://devblogs.microsoft.com/dotnet/build-your-own-ai-agent-harness-in-csharp-the-maf-claw-live-series/">Build Your Own AI Agent Harness in C#, the MafClaw Live Series</a> appeared first on <a href="https://devblogs.microsoft.com/dotnet">.NET Blog</a>.</p>
Performance Improvements in .NET 11
<p>Take a tour through hundreds of performance improvements in .NET 11.</p> <p>The post <a href="https://devblogs.microsoft.com/dotnet/performance-improvements-in-net-11/">Performance Improvements in .NET 11</a> appeared first on <a href="https://devblogs.microsoft.com/dotnet">.NET Blog</a>.</p>

My Claude Code Status Line (Steal It)
๐ Download my script here: https://gui-ferreira.kit.com/c6dd52421e #claude #claudecode
Understanding Device Bound Session Credentials (DBSC)
In this post I provide an introduction to Device Bound Session Credentials, I look at how DBSC protects against session hijacking, and how the protocol works
Share your .NET story with the community
<p>Share how your team uses .NET to solve real problems and help us bring more community stories to .NET Conf 2026 and other .NET channels.</p> <p>The post <a href="https://devblogs.microsoft.com/dotnet/share-your-dotnet-story/">Share your .NET story with the community</a> appeared first on <a href="https://devblogs.microsoft.com/dotnet">.NET Blog</a>.</p>
Rebuilding the Agent conversation: sessions, turns, thoughts, tools, MCP, skills and summaries
How to correlate Cursor hook events into sessions, turns, concurrent tool and MCP calls, detect skill usage, and build useful summaries without pretending the reconstruction is perfect.