GitHub announced that its conversational AI coding assistant Copilot Chat will be generally available this December, incorporating powerful new features like in-editor suggestions, slash commands, and security enhancements.
Powered by OpenAI's latest GPT-4 model, Copilot Chat provides context-aware guidance directly within the coding workflow. Developers can get AI-generated explanations, recommendations, and code fixes by chatting with Copilot in natural language. Here is a run-down of the new features:
- Code-aware guidance and code generation: Copilot Chat uses your code as context, and is able to explain complex concepts, suggest code based on your open files and windows, help detect security vulnerabilities, and help with finding and fixing errors in code, terminal, and debugger.
- Iterate on code with AI-powered inline Copilot Chat: with the new inline Copilot Chat, developers can chat about specific lines of code, directly within the flow of their code and editor.
- Slash commands to shortcut your big tasks: introducing slash commands and context variables to GitHub Copilot—so fixing or improving code is as simple as entering
/fixand generating tests now starts with/tests. - Apply the power of AI with a click: smart actions offer powerful shortcuts for your workflow with just a click–whether you need to fix suggestions, pull request review content, or speed up commits and pull requests with a generated response.
- Bringing Copilot Chat to JetBrains: you asked, and we heard you loud and clear. Copilot Chat will come to the JetBrains suite of IDEs, available in preview today.
Copilot Chat is available as part of an existing GitHub Copilot subscription, for organizations and individuals. It will continue to be available at no cost to verified teachers, students, and maintainers of popular open-source projects.