GitHub, the world’s leading AI-powered developer platform, today announced the general availability of GitHub Copilot Chat and previews of the new GitHub Copilot Enterprise offering, new AI-powered security features, and the GitHub Copilot Partner Program.
Thomas Dohmke, CEO, GitHub, said: “In March, we shared our vision of a new future of software development with Copilot X, where AI infuses every step of the developer lifecycle. Since then, we’ve been working to scale and mature the underlying technology–and in the process we created something even bigger. Our vision has manifested itself into a new reality for the world’s developers.
“Just as GitHub was founded on Git, today we are re-founded on Copilot. Open source and Git have fundamentally transformed how we build software. It is now evident that AI is ushering in the same sweeping change, and at an exponential pace. In just a short period, GitHub Copilot has expanded and evolved GitHub into the world’s leading AI-powered developer platform.
“We are certain this foundational transformation of the GitHub platform, and categorically new way of software development, is necessary in a world dependent on software. Every day, the world’s developers balance an unsustainable demand to both modernize the legacy code of yesterday and build our digital tomorrow. It is our guiding conviction to make it easier for developers to do it all, from the creative spark to the commit, pull request, code review, and deploy—and to do it all with GitHub Copilot deeply integrated into the developer experience,” Dohmke added.
GitHub Copilot Chat generally available in December 2023
Coding is the centerpiece of the software development lifecycle. With GitHub Copilot Chat GitHub is enabling the rise of natural language as the new universal programming language for every developer on the planet. Whether it’s finding an error, writing unit tests, or helping debug code, Copilot Chat is a users’ AI companion through it all, allowing them to write and understand code using whatever language they speak.
Copilot Chat will be generally available in December 2023 as part of users’ existing GitHub Copilot subscription, for organizations and individuals. This offering is also available at no cost to verified teachers, students, and maintainers of popular open source projects.
Copilot Chat is more available, and more powerful:
- GPT-4 powers Copilot Chat: GitHub has upgraded the Copilot Chat experience, bringing more accurate code suggestions and explanations with OpenAI’s GPT-4 model.
- Code-aware guidance and code generation: Copilot Chat uses a users’ code as context, and is able to explain complex concepts, suggest code based on their 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 big tasks: GitHub is introducing slash commands and context variables to GitHub Copilot—so fixing or improving code is as simple as entering /fix and generating tests now starts with /tests.
- Apply the power of AI with a click: smart actions offer powerful shortcuts for developer workflows with just a click – whether developers need to fix suggestions, pull request review content, or speed up commits and pull requests with a generated response.
- Bringing Copilot Chat to JetBrains: Copilot Chat will come to the JetBrains suite of IDEs, available in preview today.
GitHub Copilot Chat is coming to github.com and GitHub’s mobile app
GitHub is the place where projects get started, where developers collaborate, and where the open source community builds and maintains the world’s code. GitHub is integrating GitHub Copilot Chat directly into github.com, so developers can dig into code, pull requests, documentation, and general coding questions with Copilot Chat providing suggestions, summaries, analysis, and answers. And, combined with the power of GitHub’s advanced code search, GitHub is enabling Copilot Chat to understand and help with the latest changes to popular open source projects.
Copilot Chat will also be available in GitHub’s best-in-class mobile app, as part of users’ existing GitHub Copilot subscription. Leveraging the power of natural language, typed or spoken on iPhone and Android devices, developers will get answers to any programming question and about the repositories, files, or documentation they’re viewing in the app. They can get the job done, even when they’re not at their desk.
With Copilot in the code editor, in the CLI, and now Copilot Chat on github.com and in GitHub’s mobile app, GitHub is making Copilot ubiquitous throughout the software development lifecycle and always available in all of GitHub’s surface areas.
Introducing GitHub Copilot Enterprise: Copilot personalized to an organization
In its early stages as an autocomplete function offered in the IDE, GitHub Copilot was already making developers 55% faster. But developers often write code only around 2 hours a day, and are bogged down with mundane tasks across the software development lifecycle. What’s more, developers spend more time deciphering rather than shipping when they can’t pinpoint and solve the issues, bugs, or vulnerabilities that are unique to an organization’s codebase.
For a team of developers to deploy at the speed and scale that organization’s need to lead in the market, developers must be empowered with AI at every step of the software development life cycle, customized and fine-tuned to their codebase.
GitHub is not only sailing past the editor, it is now culminating the entirety of its Copilot offerings and personalizing them with the full context of a developer’s entire codebase with GitHub Copilot Enterprise. With Copilot Chat connected to a developer’s repositories on github.com, Copilot Enterprise allows teams of developers to quickly get up to speed on their codebase, search through and build documentation, get suggestions based on internal and private code, and quickly review pull requests. Additionally, smart actions, such as the ability to generate pull request summaries, will be available throughout GitHub helping developers stay in their flow state with the click of a button. And of course, this all comes with enterprise-grade security, safety and privacy.
GitHub Copilot Enterprise will be generally available in February 2024 for $39 USD per user per month.
Fostering an ecosystem built on Copilot with the GitHub Copilot Partner Program
Many developers rely on a complex stack of tools and services that hold crucial information about the project they are working on. Today, GitHub is announcing it will be supercharging GitHub Copilot by integrating it with third-party developer tools, online services, and knowledge outside GitHub. The GitHub Copilot Partner Program will create an ecosystem for new networks and ingenuity to be infused into GitHub Copilot, broadening the expanse of what developers can achieve with AI.
As this ecosystem continues to expand, so will the possibilities and use cases of what GitHub Copilot can accomplish for developers. From helping to improve the performance of database queries, to checking the status of a feature flag, or to viewing the results of an A/B test–all of this and more will soon be possible thanks to the partners who are building plugins for GitHub Copilot.
GitHub is kicking off the first phase of this program with over 25 of its debut partners, including Datastax, LaunchDarkly, Postman, Hashicorp, and Datadog.
New AI-powered security features available with GitHub Advanced Security
Today, GitHub Copilot applies an LLM-based vulnerability prevention system that blocks insecure coding patterns in real-time to make GitHub Copilot’s suggestions more secure. GitHub’s model targets the most common vulnerable coding patterns, including hardcoded credentials, SQL injections, and path injections.
GitHub Copilot Chat can also help identify security vulnerabilities in the IDE, explain the mechanics of a vulnerability with its natural language capabilities, and suggest a specific fix for the highlighted code. This will radically transform the traditional definition of “shift left.” Now, GitHub is infusing GitHub Advanced Security with new AI-powered application security testing features designed to detect and remediate vulnerabilities and secrets in code.
Code scanning autofix suggests AI-generated fixes using CodeQL for JavaScript and TypeScript directly in pull requests, assisting developers in resolving issues faster, and reducing the introduction of new vulnerabilities into codebases. And with AI secret scanning for generic secrets and GitHub’s new regular expression generator for custom patterns, it’s making it easier to find leaked secrets with low false positives rates.
Combined, these new detection capabilities help developers prevent and detect more security vulnerabilities across their organization, keeping code fortified for the future. These features are today available in preview and will soon be included in the GitHub Advanced Security subscription.
Coming Next: GitHub Copilot Workspace
For developers, the greatest barrier often starts at the beginning, with generating the plan it takes to stream an idea into code and all the way to the pull request. Many ideas and bugs begin in a GitHub issue. By combining the details of the issue with the knowledge of the codebase and the reasoning capabilities of GPT-4, the research team at GitHub Next has developed an AI-powered bridge to help every developer scale the barrier of putting an idea into code: the GitHub Copilot Workspace.
When users open an issue in Copilot Workspace, they’re presented with an automatically proposed plan for how to implement the intended change. Because the workspace is fully editable, they’re able to steer the AI in the exact direction they want, while benefiting from its understanding of the issue’s intent, and their entire codebase. To validate that the change behaves as expected, Copilot Workspace enables users to build, run and test the code. And if it encounters an error, it offers to fix it automatically. Copilot Workspace is like a pair programming session with a partner that knows about every inch of the project, and can follow a user’s lead to make repository-wide changes from the issue to the pull request with the power of AI.
Copilot Workspace is an early glimpse of the GitHub Next vision to investigate the future of software development. When Copilot Workspace is delivered in 2024, we will be a consequential leap closer to an age where developers can use AI as a second brain to stream their creativity into creation in minutes, all with natural language.
