Microsoft's second release candidate adds cryptography APIs, mobile and desktop development improvements, and package management controls ahead of next month's final release.

Microsoft's latest update expands agent management, adds cross-platform sandboxing and lets developers pick up AI conversations started in other apps.

Ahead of his Visual Studio Live! session, Marcel de Vries explains how .NET teams can expose useful application capabilities to AI agents, starting with focused, read-only tools and user-specific ...

VS Code's AI Toolkit Agent Builder can wire an agent to external tools via MCP, even for non-coding editorial workflows. Early friction points included circular UX flows, model availability mismatches ...

When you need to integrate authorization with procedural code, you're going to need your application's ClaimsPrincipal object so that you can check the user's authorization claims. Here's both how to ...

Random forest regression is a tree-based machine learning technique to predict a single numeric value. A random forest is a collection (ensemble) of simple regression decision trees that are trained ...

Microsoft now ships Azure MCP tools as part of the Azure development workload in Visual Studio 2022 version 17.14.30 or higher. Other MCP-related items that later appeared in the Visual Studio 2022 17 ...

VS Code 1.137 adds Preview Automations for recurring agent tasks on schedules. Experimental Voice Mode supports spoken agent conversations with interruption and session awareness. Experimental GitHub ...

Researchers analyzing GitHub Copilot telemetry found that about 87 percent of LLM calls were agent-initiated after a developer began a turn. LLM calls and tool invocations occurred at nearly a 1:1 ...

Seven social media posts preview changes spanning Markdown image handling, merge conflicts, keyboard shortcuts, testing and AI chat.

Microsoft's .NET 11-era overhaul adds project caching, Native AOT, faster builds and richer project-file tooling.

Microsoft's enterprise Copilot example highlights a broader shift toward reusable packages of AI instructions, skills and tools.