DEVOPSdigest

GitHub announced a wave of new features and enhancements to GitHub Copilot to streamline coding tasks based on an organization’s specific ways of working.

This includes agentic capabilities for implementing changes across multiple files, next edit suggestions to automatically predict and execute the next logical edit, and the ability to store and share tailored instructions for Copilot directly in the editor. GitHub also unveiled a first look at a new autonomous SWE agent, and announced general availability of Copilot Edits, availability of Google’s Gemini 2.0 Flash and OpenAI’s o3-mini for Copilot Chat and Edits, and enterprise support for Copilot Workspace. Businesses can immediately enable organization-wide access to increase developer productivity and accelerate time from code to production at scale.

“Developer teams will soon be joined by teams of intelligent, increasingly advanced AI agents that act as peer-programmers for everyday tasks,” said GitHub CEO Thomas Dohmke. “With today’s launch of GitHub Copilot agent mode, developers can generate, refactor and deploy code across the files of any organization’s codebase with a single prompt command. Organizations who empower their developers to work with these agents will exist in another spectrum of productivity entirely.”

Copilot Edits is now generally available, enabling users to specify a set of files to be edited and then use natural language to ask Copilot what changes should be made. Copilot Edits makes inline changes directly in the user's workspace, across multiple files, and with a UI designed for fast iteration.

The following new preview features can be leveraged in Visual Studio Code today:

- Agent mode enables Copilot to iterate on its own output as well as the results of that output to complete a user’s entire request at once, recognize and fix errors automatically, suggest terminal commands, and analyze run-time errors with self-healing capabilities.

- Next edit suggestions to accelerate code changes by automatically identifying and proposing the next edit based on the context of previous changes. By simply pressing tab, users can instantly implement suggestions throughout an open file with insertions, deletions, and replacements.

- Prompt files allow users to store and share reusable prompt instructions in their VS Code workspace. These “blueprints” include self-contained markdown files that blend natural language guidance, file references, and linked snippets to supercharge coding tasks.

- Vision for Copilot enables users to bring a mock up to life by simply feeding Copilot a snip, screenshot, or image. From there, Copilot generates the UI, alt text, and code to go from vision to reality in minutes.

- New models from industry leaders Google’s Gemini 2.0 Flash and OpenAI’s o3-mini are now available in public preview in Copilot Chat with organization-wide access control to give administrators more choice over which models they want their developers to build with.

GitHub also announced provisioning and authentication support for Copilot Workspace for Enterprise Managed Users, empowering organizations to configure and control Workspace access securely. Now developer teams can use Copilot Workspace’s agentic capabilities to go from brainstorm to functional code in minutes. Whether generating a plan, implementing code, or automatically finding and fixing errors, Copilot Workspace leverages a system of sub-agents to iterate with developers at every step and streamline collaboration across teams.

Finally, GitHub unveiled its plans for an autonomous agent to independently handle entire tasks at the developer’s direction called “Project Padawan.” This represents a future where developers can assign issues to Copilot, let the AI complete the task autonomously, and come back to review its work. Just as it did with Copilot Extensions and adding multi-model choice to GitHub Copilot, GitHub will provide opportunities for partners and customers to integrate into this AI-native workflow and use their feedback to inform its development.