Personal custom instructions are now available in public preview for Copilot on github.com 🎉

Copilot Chat on github.com now supports personal instructions! This means you can provide Copilot with important details about your preferences, such as your preferred language, response style, or even code standards.

To get started, open up Copilot Chat, click ..., and select Personal instructions. That’s it! Copilot will now incorporate your preferences for all chats in github.com.

💡 Looking for ideas? Here are some examples to kick things off:

• Language preferences: “Always respond in Portuguese.”
• Response preferences: “Be concise and to-the-point. Always cite your sources.”
• Personal preferences: “You are a seasoned React developer with ten years of experience.”
• Code preferences: “Always provide examples in TypeScript.”

Looking for more? Visit prompts.chat for more inspiration.

Search the web 🔍 in Copilot chat using Bing

Copilot Chat can now search Bing to answer questions and find information beyond its general knowledge or your codebase. This feature makes it easy to chat about recent events, trends, and new developments. It’s now generally available in VS Code, Visual Studio, and github.com.

Since our public preview, we’ve enhanced our web search capabilities to deliver more relevant and accurate responses to your questions.

Give it a try today:

• “What’s the latest version of React?”
• “What are the most recent updates in Python’s machine learning libraries?”

Quality improvements to Copilot Chat

In the last month, we have delivered a collection of quick wins and subtle enhancements ✨, making the product smoother and more delightful for everyone.

What’s new:

• Better search in Copilot Chat for more relevant and complete answers, including expanded lexical search results and larger semantic search responses for better context
• Improved memory in Copilot, now keeping more of your chat history for better context and flow
• Improved Copilot Chat’s awareness of the README.md when asking about a repository
• Enhanced Copilot’s awareness of time, showing times relative to you instead of UTC

We also recently added the ability to view and generate new code files to Copilot chat at github.com/copilot – check it out!

OpenAI’s latest model, o3-mini, is now available in GitHub Copilot Free.

OpenAI’s latest model, o3-mini, is the most cost-efficient model in their reasoning series. o3-mini outperforms o1 on coding benchmarks with response times that are comparable to o1-mini, meaning you’ll get improved quality at nearly the same latency. The model is configured to use OpenAI’s medium reasoning effort and can be accessed in VS Code and Github.com Copilot chat today, with support to follow soon in Visual Studio and JetBrains.

Access to o3-mini is currently in preview and is subject to the 50 free chats per month limit when using Copilot Free.

Get started with Copilot Free on GitHub and in VSCode today or learn more in our documentation.

Announced at GitHub Universe 2024, Gemini 2.0 Flash is now available to all GitHub Copilot customers, including Copilot Free. The latest Gemini model from Google shows high capabilities for code suggestions, documentation, and explaining code.

Get started today!

Copilot Free or Pro users

You can start using the new Gemini 2.0 Flash model today via the model selector in Copilot Chat in Visual Studio Code and immersive chat on GitHub.com.

Copilot Business or Enterprise users

Copilot Business and Enterprise organization administrators will need to grant access to Gemini 2.0 Flash in Copilot via a new policy in Copilot settings. Once enabled, you will see the model selector in VS Code and chat on GitHub.com. You can confirm availability by checking individual Copilot settings and confirming the policy for Gemini 2.0 Flash is set to enabled.

Share your feedback

Join the community discussion to share feedback and tips.

For additional information, check out the docs on Gemini 2.0 Flash in Copilot.

Elevate your coding skills with our redesigned Copilot Chat, now featuring a dedicated home on GitHub.

What’s new in Copilot Chat on GitHub:

• Immersive chat experience at github.com/copilot: Copilot is now just one click away, offering a seamless and immersive chat directly on GitHub.
• Smarter and faster responses: Whether you’re brainstorming, problem-solving, or just exploring ideas, Copilot’s answers are sharper, richer, and more naturally attuned to your needs.
• Real-time interaction with your codebase: Ask questions and get immediate answers about your codebase, helping you understand how things work faster than ever.
• Generate and refine code effortlessly: Use conversational prompts to create and refine code snippets or entire files. Iterate seamlessly until you achieve the desired outcome.
• Navigate GitHub with natural language: Summarize issues and pull requests, retrieve specific information, and explore repositories without navigating through the UI.
• Leverage a variety of models: Choose from different AI models to get the best results based on your specific use case.
• Find and return to previous chats: Easily revisit past conversations, keep track of important insights, code iterations and decision-making processes by accessing your entire conversation history whenever you need it.

Expanded capabilities across your entire codebase

As part of this update, we’ve removed limits on how many repositories you can index. Now, you can enjoy the full capabilities of Copilot Chat across your entire codebase, whether you’re working on multiple projects or a large monolith.

Your feedback helps us continue to improve. Let us know what you think using the in-product feedback option or pop it into the GitHub Community at any time.

Copilot Chat on GitHub.com, GitHub Mobile, the GitHub CLI, as well as officially supported IDEs now have a 64k token window available when working with OpenAI GPT-4o. With this change, customers working with large files and repositories should expect improved responses from Copilot. This change helps Copilot retrieve more information when executing skills to provide contextually relevant responses.

There is no action required on your part to benefit from this upgrade, it is automatically available for all GitHub Copilot users. For more information, check out our documentation and join the discussion within the GitHub Copilot Community.

Hungry for more? – 128k token window for VS Code Insiders

If you’re using GitHub Copilot with Visual Studio Code Insiders, you have access to an even larger 128k context window – the maximum supported by OpenAI GPT-4o. Download the Insiders build to try it out.