Whereas the agentic shift has made improvement sooner, it’s additionally led to disjointed workflows, extra context switching, and an excessive amount of time spent reviewing agent-generated code.
If brokers are going to be a sturdy a part of how software program will get constructed, they want an actual place within the developer workflow. But most developer instruments weren’t designed for steering a number of brokers in parallel. Context scatters throughout home windows. You lose observe of what’s working. Code lands in pull requests with out a clear path of what the agent tried, what it validated, or the place human judgment is required.
| Get began with the GitHub Copilot app as we speak utilizing your current Copilot Professional, Professional+, Enterprise, or Enterprise plan. Learn more > |
Throughout GitHub, builders are utilizing brokers to maneuver from immediate to plan, from difficulty to tug request, from evaluation suggestions to merged code. As agentic workflows turn into the norm, repository creation, pull request exercise, and API utilization are all accelerating with no proof of slowing down. On GitHub alone, commits practically doubled 12 months over 12 months, crossing 1.4 billion per 30 days, plus over 2 billion GitHub Actions minutes every week.
To fulfill this demand and proceed to be the house for all builders (and now their brokers), our focus is scaling our underlying methods and enhancing resilience and stability throughout all of our providers, at each layer of the stack.
GitHub is constructing that system for the agentic frontier, and that’s what we’re displaying as we speak at Microsoft Construct.
Copilot app: A management middle for agent-native improvement
You begin the day with three items of labor already in movement. One agent is investigating a manufacturing bug. One other is implementing a backlog difficulty. A 3rd is working via evaluation suggestions on a pull request. Every is working in its personal remoted surroundings, producing modifications you may examine, redirect, check, and merge.
You want an surroundings that may sustain.
The brand new GitHub Copilot app is the agent-native desktop expertise constructed on GitHub. From a single My Work view, you may see work in movement throughout related repositories: energetic periods, points, pull requests, and background automations. The Copilot app is now accessible in technical preview for current Copilot Professional, Professional+, Enterprise, and Enterprise customers.
The GitHub Copilot app is the newest in a line of AI tooling from GitHub that’s reworking our enterprise. Transferring past AI help, the app has supplied a much-needed management middle for agentic improvement.
Our Ahead Deployed Engineers can dispatch a cohort of brokers and handle a number of initiatives, all from one location. Easy accessibility to plans and autopilots with the flexibility to run interactive periods or step into code the place wanted.
David Jobling | Grasp Expertise Architect, Head of Expertise & Supply Futures, World Solutioning & Supply, Avanade Inc.
Each session runs in its personal git worktree, an actual, remoted copy of your department. This helps parallel agent periods work with out stepping on one another. The app handles each worktree for you: no handbook setup, no cleanup, no department juggling. Whether or not you begin from a immediate or a problem out of your inbox, Copilot will get the context it wants from current points, pull requests, and the repos you’ve related.
Then Agent Merge helps carry that pull request via evaluation, checks, and merge. It displays CI, tracks required reviewers, addresses failing checks, and waits for all situations to be happy. You select how far Copilot ought to go: drive CI again to inexperienced, handle suggestions, or merge when your situations are met. You resolve what automation is enabled and what ships.
Canvas: The place intent turns into inspectable work
Chat is highly effective for instruction and ambiguity. However as soon as an agent begins doing actual work, a chat thread turns into a protracted scroll of choices, logs, and corrections. You want a spot the place the work itself is seen.
Right now, we’re additionally introducing canvases in the GitHub Copilot app. Canvases are bidirectional work surfaces for people and brokers. A canvas would possibly present a plan, pull request, browser session, terminal, deployment, dashboard, or workflow state. Brokers replace the canvas as they work, and builders can edit, reorder, approve, or redirect that work on the identical floor.
That is the start of agent expertise (AX) within the Copilot app: interfaces the place folks and brokers function collectively. Chat is the place you instruct, focus on, and cause via ambiguity. Canvases are the place that intent turns into seen work you may examine, steer, and confirm.
Brokers that may solely recommend code go away you do plenty of the work. To be more practical, brokers have to run code, examine outcomes, check modifications, and iterate, with out touching manufacturing.
Cloud and local sandboxes for GitHub Copilot give brokers a bounded place to behave. Select the place Copilot runs—in your native machine or within the cloud—and start unlocking agent-driven workflows whereas prioritizing safety and enterprise coverage enforcement, and with out native useful resource constraints.
With native sandboxing, Copilot runs in an remoted surroundings immediately in your machine, with restricted entry to filesystems, community connectivity, and system capabilities. Native sandbox insurance policies may be centrally configured and enforced.
Within the cloud, every sandbox runs in a completely remoted, ephemeral Linux surroundings hosted by GitHub. Organizations outline their very own insurance policies. From the cloud, you may choose up Copilot periods wherever, on any system, with distant management.
Code evaluation that scales with agentic output
As brokers produce extra pull requests, the strain on code evaluation compounds. Copilot code review brings an adaptable, agentic system to filter via the noise, permitting you to focus your power the place it issues most whereas Copilot conducts code opinions.
Now you can prolong Copilot so each evaluation displays your individual requirements, inside methods, and engineering context by way of customized agent expertise, MCP server connections, and configurable actions workflows.
Copilot code evaluation now affords medium tier review, which routes pull requests to a higher-reasoning mannequin for higher precision and recall. Admins can set tips for particular person repositories to “low” or “medium.” This allows you to assign lighter, cost-efficient fashions for low-risk code and save extra sturdy mannequin use for repos with greater affect.
The /security-review ability provides Copilot a devoted path for security-focused analysis. The /rubberduck ability is now typically accessible to make use of a number of mannequin households to critique your implementation and discover novel points.
And if you happen to’re engaged on Azure DevOps, now you can use Copilot code review natively. Get the identical one-click evaluation, inline feedback, and committable repair strategies you anticipate, and admins can allow code evaluation on whichever repos they need.
The identical agentic capabilities work throughout the terminal, the cloud, and even your individual instruments, on the identical basis.
Now you can construct your individual instruments with the GitHub Copilot SDK. Now typically accessible in Node.js/TypeScript, Python, Go, .NET, Rust, and Java, it exposes the identical agentic runtime that powers the Copilot app. In case your workforce wants an inside code evaluation software, a customized release-notes generator, or an agent embedded in a help workflow, you construct it on the identical basis as an alternative of wiring collectively a bespoke stack. One runtime, many surfaces.
For builders preferring to work within the terminal, Copilot CLI now has a redesigned interface, voice enter, and scheduled duties to maintain you there.
Copilot CLI has a redesigned TUI in /experimental mode with tabbed entry to tug requests, points, and gists from the terminal. Voice mode makes use of on-device speech-to-text, so audio by no means leaves your machine. /each schedules recurring prompts and background duties.
Cloud automations let brokers run on a schedule, reply to GitHub occasions, open points, and go away feedback. By default, the cloud agent asks permission earlier than every write motion. Swap to autopilot after getting established belief.
Engineering doesn’t finish with writing code. It consists of submitting the difficulty, kicking off the dialogue, and replying to reviewers. Copilot cloud agent can now deal with each a kind of steps.
Reminiscence++ and /chronicle give Copilot continuity throughout gadgets and over time. Question context from periods began within the app, CLI, VS Code, or on GitHub.
Accomplice-built agent apps combine with GitHub Copilot to assist automate duties, generate code, analyze context, and execute actions. Use your favourite instruments with out leaving GitHub. Assign points to new brokers that suit your workflow. Companions embody LaunchDarkly, Shiny, Amplitude, Sonar, Endor Labs, Octopus Deploy, Packfiles, PagerDuty, and Miro. Begin utilizing these agent apps as we speak. And be a part of the waitlist so your organization may deliver its personal agent apps to GitHub.
What we’re constructing towards
Skilled software program calls for judgment, verification, and accountability. That’s the reason the GitHub Copilot app, sandboxes, code evaluation, automation, context, and accomplice ecosystem are coming collectively as one system: brokers can do extra of the work, whereas builders hold management of high quality, coverage, and supply.
As agentic workflows develop throughout GitHub, from repository creation to tug request exercise and API utilization, the platform has to develop with them. We are going to proceed to give attention to availability first. We’re dedicated to hardening these methods so agent-native improvement is quick, accessible, and dependable sufficient for groups to depend upon every single day.
GitHub is the place that system lives, as a result of it’s already the place the code, the opinions, the problems, and the groups are.
Let’s construct.
Be taught extra about our launches from Microsoft Construct on the GitHub Changelog >
Written by
