/smstreet/media/media_files/8WdciPGo3O5mGmfBGgf2.jpg)
GitHub is launching a new Agents experience on GitHub—the Agents panel—allowing users to quickly delegate tasks to Copilot from any page on github.com with a simple prompt, and track Copilot’s progress without breaking flow.
The Agents panel, available today for all paid GitHub Copilot plans (Pro, Pro+, Business, Enterprise) on every page on github.com, is a developer’s mission control center for agentic workflows on GitHub. It’s a lightweight overlay that allows developers to hand new tasks to Copilot and track existing tasks without navigating away from current work.
And of course, Copilot coding agent is also integrated into VS Code, GitHub Mobile, and the GitHub MCP Server, so users can collaborate with Copilot wherever they’re working.
From the Agents panel, developers can:
Assign background tasks without switching pages
Monitor running tasks with real-time status
Jump into pull requests when ready to review
Developers can start a new Copilot task from the new Agents panel with a simple prompt. They just open the panel from any page on GitHub, describe the goal in natural language, and select the relevant repository. Copilot will then take it from there and start creating a plan, drafting changes, running tests, and then preparing a pull request.
Copilot coding agent: a quick reintroduction
Copilot coding agent lets developers hand off coding tasks—via GitHub.com, GitHub Mobile, VS Code, or any MCP-enabled tool—and get back a draft pull request when it’s done. It runs in the cloud, can work in parallel on multiple tasks, and continues even if a developer’s computer is off.
Its secure, GitHub Actions-powered environment can run builds, tests, and linters without asking for every step. Developers stay in control with detailed logs and pull request-based approvals, and can give feedback by mentioning @copilot in a review.
Thanks to the Model Context Protocol (MCP), Copilot has read access to a developer’s repository data on GitHub (powered by the GitHub MCP Server). It can also view web pages for testing and validation (powered by the Playwright MCP Server), and connect to a user’s own MCP servers, as well.