The .NET Community Blog
Where .NET developers
|
Deep dives, tutorials and community stories — written by developers, for developers.
The Coding Harness: Why the Model Matters Less Than You Think
The coding harness assembles context, exposes tools, runs the agent loop, and evaluates behavior. Understanding that layer is central to reliable .NET workflows in VS Code.
Agentic DevOps Foundations: Four Agent Types and When to Use Them
A practical introduction to local, CLI, cloud, and third-party agents, with guidance for .NET teams choosing execution models and building reusable agent workflows.
The Agentic DevOps Playbook: From Broken Practices to Agent-Ready Delivery
Agents accelerate what a team does well and what it does poorly. A practical playbook for strengthening DevOps foundations, specifications, pipelines, and governance.
MCP Apps on Azure Functions: Moving Beyond Text-Only Interfaces
Azure Functions can host MCP tools and interactive UI resources, giving AI clients dashboards, forms, and workflow interfaces alongside structured responses.
VS Code 1.113: Agent Workflows, Chat Customization, and the Thinking Model
VS Code 1.113 brings unified chat customizations, configurable thinking effort, nested subagents, and MCP support to CLI agent workflows.
VS Code 1.112: What .NET Developers Should Actually Care About
VS Code 1.112 just dropped and it's packed with agent upgrades, an integrated browser debugger, MCP sandboxing, and monorepo support. Here's what actually matters if you're building with .NET.
Run and Test AI Agents Locally with Azure Developer CLI
New azd AI agent commands shorten the inner loop by starting agents locally and invoking local or remote sessions from the terminal.
How VS Code Builds with AI: Lessons from Weekly Releases
The VS Code team's AI-assisted development workflow offers practical lessons in parallel work, issue triage, automated validation, and human judgment.
VS Code 1.111: Agent Workflows Gain Autonomy and Debug Visibility
VS Code 1.111 adds session-level permission modes, Autopilot preview, agent-scoped hooks, and debug snapshots for safer autonomous workflows.