10 results found

• Set up a context engineering flow in VS Code

  Set up a context engineering flow in VS Code This guide shows you how to set up a context engineering workflow in VS Code using custom instructions, custom agents, and prompt files. Context engineering is a systematic approach to providing AI agents with targeted project information to improve the quality and accuracy of generated code. By curating essential project context through custom ...

• UX Guidelines | Visual Studio Code Extension API

  UX Guidelines These guidelines cover the best practices for creating extensions that seamlessly integrate with VS Code's native interface and patterns. In these guidelines, you can expect to find: An outline of VS Code's overall UI architecture and elements Recommendations and examples for UI contributed by an extension Links to relevant guides and samples Before diving into the details, it's ...

• AI features in VS Code

  Concepts The following conceptual articles explain the architecture and building blocks that power these AI features: Language models: the AI models that power all features, including how to choose and configure them. Context: how VS Code assembles information for the model, from your files to conversation history.

• Use custom instructions in VS Code

  Learn how to create custom instructions for GitHub Copilot Chat in VS Code to ensure AI responses match your coding practices, project requirements, and development standards.

• Documentation for Visual Studio Code

  Your home for multi-agent development. Explore AI agents, coding tools, extensions, and everything you need to build faster with Visual Studio Code.

• Introduction to agent-first development - Visual Studio Code

  Learn how harness, model, context, tools, and prompt work together for effective agent-first development in VS Code.

• Agents - Visual Studio Code

  Agents An agent is an AI system that autonomously plans and executes coding tasks. You give the agent a high-level goal, and it breaks the goal down into steps, executes those steps with tools, and self-corrects when it hits errors. This article explains the core architecture of agents: the agent loop, agent types, subagents, memory, and planning. Agent loop When you give an agent a task, it ...

• Supporting Remote Development and GitHub Codespaces

  Supporting Remote Development and GitHub Codespaces Visual Studio Code Remote Development allows you to transparently interact with source code and runtime environments sitting on other machines (whether virtual or physical). GitHub Codespaces is a service that expands these capabilities with managed cloud-hosted environments that are accessible from both VS Code and a browser-based editor. To ...

• MCP developer guide | Visual Studio Code Extension API

  MCP developer guide Model Context Protocol (MCP) is an open standard that enables AI models to interact with external tools and services through a unified interface. Visual Studio Code implements the full MCP specification, enabling you to create MCP servers that provide tools, prompts, and resources for extending the capabilities of AI agents in VS Code. MCP servers provide one of three types ...

• Customization - Visual Studio Code

  Customization AI models have broad general knowledge but don't know your codebase or team practices. Think of the AI as a skilled new team member: it writes great code, but doesn't know your conventions, architecture decisions, or preferred libraries. Customization is how you share that context, so responses match your coding standards, project structure, and workflows. This article explains ...