Over the past two years, generative AI has helped accelerate what programmers can do. Now, GitHub is giving them even more tools. On Monday, the company launched a technical preview of GitHub Copilot Workspace, an AI-powered developer environment. The release builds on GitHub’s existing productivity tools, including GitHub Copilot, launched in 2022, and Copilot Chat, which lets programmers use natural language to test and debug their code. “Within Copilot Workspace, developers can now brainstorm, plan, build, test, and run code in natural language,” the announcement explains. “This new task-centric experience leverages different Copilot-powered agents from start to finish, while giving developers full control over every step of the process.” Copilot Workspace gives developers end-to-end AI support on whatever they’re building, aiming to assist where many programmers get blocked: the beginning of a project. Starting with a GitHub repository or issue, engineers can work with AI-powered agents to address bugs and test possible solutions. Because Copilot Workspace is familiar with the codebase and previous issue replies, the tool can then suggest and take steps to try to resolve the problem, all written in natural language. All of Copilot Workspace’s steps and code suggestions are editable, meaning developers maintain control over what’s deployed, but don’t have to build every component to get there. Developers can run their final code in Workspace, make tweaks in GitHub Codespace, and share a link to their workspace with other team members, who can see how they used Copilot agents to realize the final product.
Full report : GitHub’s new Copilot Workspace lets developers ‘go from idea, to code, to software in natural language.’