Content by Visual Studio Code (166)
Visual Studio Code shares a quick set of “top tips” from the engineering team, highlighting practical editor features like subagents, favorite shortcuts, and a few hidden easter eggs, plus a mention of event agent markdown files and GitHub Copilot-related workflows.
Visual Studio Code introduces “bring your own key” support, letting developers use their own model provider API keys with VS Code and GitHub Copilot without signing in, and points to the setup guide for enabling expanded model choice.
Visual Studio Code shows how to use VS Code’s language model system to bring your own AI provider without signing into Copilot, including native providers like Anthropic, custom endpoints, third-party integrations, and running local models offline.
Visual Studio Code shares a quick walkthrough of three MCP servers they use daily in VS Code—GitHub, Playwright, and Microsoft Learn—to extend GitHub Copilot Agent mode for PR review, real-browser testing, and pulling up-to-date documentation as context.
Visual Studio Code highlights new Integrated Browser improvements in VS Code, including saving browser favorites, taking full-page or region screenshots, and using browser content as context for GitHub Copilot and agent workflows.
Visual Studio Code shows how the Mermaid Markdown Features extension renders Mermaid diagrams directly in VS Code, including Markdown Preview, notebook Markdown cells, and VS Code Chat, so teams can keep architecture and workflow diagrams alongside their docs and code.
Visual Studio Code hosts the final Agents League challenge, where experts build business-ready knowledge agents integrated with Microsoft 365 and authored in Copilot Studio, and the audience is sent into a last sprint before the hackathon closes on June 14.
Visual Studio Code hosts an Agents League session where experts demonstrate building reasoning-based AI agents with Microsoft Foundry, focused on solving complex problems and helping participants apply the approach in their hackathon submissions.
Visual Studio Code kicks off the Agents League with a creative app-building battle, where experts demonstrate AI-assisted development using GitHub Copilot and share ideas participants can apply to their own hackathon submissions.
Visual Studio Code hosts a Microsoft Build 2026 live stage session with demos and discussion spanning GitHub Copilot, the Copilot SDK, and VS Code workflows. It touches on agent integration, multi-model verification, security concerns in AI code review, and developer tooling updates shared by the teams building them.
Visual Studio Code hosts a live Microsoft Build session with the GitHub Copilot team, covering agentic development across the Copilot ecosystem. The agenda includes Copilot CLI, building with the GitHub Copilot SDK, and a segment on .NET Aspire alongside Copilot and related tooling.
Visual Studio Code shares a short clip about “Copilot Teaches”, pointing to a longer explanation of how GitHub Copilot customization works in VS Code using concepts like instructions, skills, and hooks.
GitHub hosts a Microsoft Build 2026 Day 2 live stream focused on what’s new in GitHub Copilot and Visual Studio Code, featuring product updates, live demos, and announcements from the teams building the tools.
Visual Studio Code shows how to run skills in a dedicated sub-agent in @code so your main Copilot Chat context stays clean and focused.
Visual Studio Code shares a short tip on when to use prompts versus relying on defaults, focusing on prompt customization in the VS Code workflow.
Visual Studio Code introduces how Copilot Agents in VS Code can use tools safely, covering what tools and tool sets are, how permissions work, and how sandboxing helps control what an agent is allowed to do during a run.
Visual Studio Code highlights a VS Code “hook” feature and points to a longer video that goes deeper on how hooks can be used to customize the editor experience.
Visual Studio Code introduces the new Agent Customization window, showing how developers can tailor agent behavior and related settings directly in the editor.
Visual Studio Code highlights the Chat Customizations Evaluation extension for VS Code, which helps developers review and refine prompts, agents, and instructions files as part of an AI-focused workflow.
Liam Hampton introduces Agent Plugins in Visual Studio Code and shows how they extend GitHub Copilot agents with additional tools. The session focuses on installing plugins and understanding how agent tooling fits into the VS Code Copilot agents workflow.
Visual Studio Code features Reynald Adolphe demonstrating how to create and use Custom Agents in VS Code (Agent Mode) so GitHub Copilot can take on specialized roles—like a security reviewer—using your project context, tools, and workflow to produce more focused results.
Visual Studio Code features Reynald Adolphe explaining how Agent Skills in VS Code package instructions, scripts, and resources into reusable workflows, with a quick demo of creating and modifying a skill to automate multi-step tasks like updating docs and generating prompts.
Visual Studio Code features Reynald Adolphe using GitHub Copilot in VS Code to explain and compare customization features—Custom Instructions, Prompt Files, Agent Skills, Custom Agents, and Hooks—plus ways to learn them via charts, quizzes, and scenario-based references.
Visual Studio Code features Reynald Adolphe explaining GitHub Copilot Hooks in VS Code: how to run commands automatically at specific lifecycle events during an agent session to keep formatting, validations, and scripts consistent without manual steps.
Visual Studio Code shows how to use Prompt Files in VS Code to stop rewriting the same GitHub Copilot instructions, making repeatable workflows (like quizzing open files or simplifying code) easier to run and share across projects and teams.
Visual Studio Code features Reynald Adolphe explaining how GitHub Copilot Custom Instructions in VS Code work in practice, showing how to create reusable “rulebooks” that steer Copilot toward your coding standards, conventions, and preferences (including SOLID and accessibility) without repeating guidance every time.
Visual Studio Code shows how to customize AI in VS Code using agent-based building blocks—agents, skills, instructions, prompt files, and hooks—so teams can reuse prompts, enforce standards, and streamline common development tasks.
Visual Studio Code shows Reynald building a “Repo Analyzer” app in VS Code using GitHub Copilot customization features—Prompt Files, Custom Instructions, Agent Skills, Custom Agents, and Hooks—to enforce repo standards, update docs, and streamline coding tasks in one workflow.
Visual Studio Code hosts a conversation with Pierce Boggan on how VS Code’s agent loop works behind AI-driven coding assistance, covering agents and sub-agents, tool usage, why different models are chosen for different tasks, and the trade-offs involved when customizing workflows.
Visual Studio Code presents a Let it Cook x AspiriFridays episode on using VS Code with .NET Aspire (Project Aspire) to give AI agents visibility into distributed application architecture, aiming to help developers build more observable cloud-native systems.
Visual Studio Code shows how to install and use your own MCP server with the GitHub Copilot CLI, pointing to an example MCP server repo you can try.
Visual Studio Code shares a short video walkthrough of improvements to VS Code terminal tools for agent sessions, covering foreground terminal support, interactive input handling, progress messages, and background notifications to make command-driven workflows smoother.
Visual Studio Code hosts a VS Code Live session where Joel Norman and Jorge Balderas use GitHub Copilot Modernization in VS Code to try modernizing a legacy .NET application, with links to the official Modernize .NET resources and repo.
Visual Studio Code highlights key changes in VS Code v1.114 that improve the GitHub Copilot Chat experience, including preview videos in the chat image carousel, copying chat responses as markdown, troubleshooting chat issues, and updates to the #codebase command.
Visual Studio Code shares a video where Liam demonstrates creating and installing a Formula 1-inspired Model Context Protocol (MCP) server in Python using FastMCP, including how the client/server flow works, STDIO transport, and how tools are discovered and invoked.
Visual Studio Code hosts a conversation with Elijah King and Thoa Nguyen about practical AI-assisted design workflows in real codebases, including using VS Code with GitHub Copilot (CLI/chat/models), plan mode, parallel sessions, and worktrees to prototype and collaborate with engineers.
Visual Studio Code shows how multi-agent support in VS Code lets developers run multiple agent sessions side by side to work on different coding tasks in parallel, such as implementing color themes, adding storage functionality, and generating documentation.
Visual Studio Code shares a hands-on video with Burke Holland and James Montemagno that builds a GitHub Copilot SDK project from scratch, focusing on what you need to get started with the Copilot SDK and related tooling.
Visual Studio Code explains how Agent Skills let you package reusable instructions and resources for a coding agent in VS Code, load them on demand, and invoke them from chat via slash commands like /skill-name.
Visual Studio Code shows how its experimental Agentic Browser Tools let agents open pages, read content, click elements, and verify changes from the integrated browser while you build a web app.