Feb 26, 2025 · With Visual Studio 2022 version 17.11, GitHub Copilot Enterprise subscribers can now use @github in chat to include context from their entire repository and to search the web (if search is enabled by your admin).

Provide Copilot with helpful context: If you are using Copilot in your IDE, open relevant files and close irrelevant files. In Copilot Chat, if a particular request is no longer helpful context, delete that request from the conversation.

Learn how to use context passing with your Copilot agent. GitHub Copilot Extensions can access certain contextual information using context passing. Context passing allows agents to receive relevant details about a user’s current file, selected text, and repository.

For example, the GitHub MCP server allows you to use Copilot Chat in Visual Studio Code to perform tasks on GitHub. You can also use MCP to create new tools and services that work with Copilot Chat, allowing you to customize and enhance your experience. For more information on MCP, see the official MCP documentation.

Oct 4, 2023 · GitHub Copilot analyzes the context in the file you are editing, as well as related files, and offers suggestions from within your text editor. GitHub Copilot is powered by a generative AI model developed by GitHub, OpenAI, and Microsoft."

Mar 29, 2023 · Copilot draws context from the code editor. It does not need access to your repositories. The code context sent to the model is commonly called a "prompt". We're constantly experimenting with new ways to create prompts that will tease even higher-quality suggestions out of …

Mar 25, 2024 · GitHub Copilot is a powerful AI assistant. Learn practical strategies to get the most out of GitHub Copilot to generate the most relevant and useful code suggestions in your editor.

Copilot chat context. This article describes how to add context to your Copilot chat prompt in Visual Studio Code to help Copilot give you the best and most relevant answers. Copilot supports different types of context, including files, symbols, terminal command output, and more.

To generate a suggestion for chat on GitHub.com, such as providing an answer to a question from your chat prompt, GitHub Copilot creates a contextual prompt by combining your prompt with additional context including previous prompts, the open pages on GitHub.com as well as retrieved context from your codebase or Bing search.

Finally, this context is used by GitHub Copilot to answer your question. If the context is too large, only the most relevant parts of the context are used. The response is marked up with references to files, file ranges, and symbols. This enables you to link directly from the chat response to the corresponding information in your codebase.