GitHub Copilot Projects Preview: Keep Human Acceptance Across Multi-Repository Work
Combine repositories, designs, Slack threads, and meeting notes in one project while keeping agent results subject to review
Key takeaways
GitHub announced Copilot Projects in public preview on October 28, 2026. A project can combine multiple repositories, design mocks, Slack threads, and meeting notes, then coordinate as many agents as needed and return results such as pull requests for review. Project automations can repeat work when a trigger occurs. That broader context is useful for features that span code and design, but it also makes acceptance criteria and tool permissions more important. This article provides a small multi-repository trial template with defined inputs, allowed tools, expected artifacts, stop conditions, and human acceptance so an agent result is not mistaken for completed work.
By ENHE AI · 2026-11-02 · AI-assisted drafting and editorial checks.
Direct answer: Projects organizes complex work, but returned results are not accepted results
GitHub announced Copilot Projects in public preview on October 28, 2026. It keeps a goal, multiple repositories, and external context in one project, coordinating one or more agents to prepare results. A project owner still defines completion, reviews diffs, and accepts or rejects each artifact.
Write a minimum project fact card first
Projects can include repositories, design mocks, Slack threads, or meeting notes as context. For the first trial, include only two relevant repositories and one design requirement. Record the goal, allowed directories, prohibited production data, required tests, and final owner.
Choose models, tools, and expected artifacts
Enable only the tools needed for the task. Require a change list, a pull request per repository, test evidence, and unresolved questions. Copilot coordinates agents as needed and brings back results such as pull requests for review. That review step cannot be skipped.
Automation triggers and stop conditions
Projects supports project automations for repeatable tasks. A trigger might be a feature release, but the automation should stop and notify an owner when permissions widen, tests fail, an unknown repository appears, cost is abnormal, or public publication is required. Repetition does not remove judgment.
Frequently asked questions
Must every project include a repository?
No. GitHub gives a launch-plan example using specifications, designs, and assets without a repository, but outputs and permissions still need to be defined.
Will agents automatically merge pull requests?
GitHub says results are returned for review. Commit, merge, and publication should continue to follow repository policy and explicit human authorization.
Why this matters
Projects addresses the coordination cost of multiple repositories, external context, and agents. The real gain comes from clearer inputs, acceptance, and failure recovery, not from treating a higher agent count as higher quality.
Related tools and reading
These pages support the same task, workflow, or risk boundary.
- Copilot cloud sessions and shared entitlement
- Copilot image generation public preview
- Repository plugin defaults and enterprise controls
Conclusion
For the first trial, use two non-production repositories and one testable design request. Require a change list, pull requests, and unresolved items. Expand Projects only when each result traces back to an input, permissions remain narrow, tests pass, and an owner accepts the outcome.
What this means for everyday users
Projects supports project automations for repeatable tasks. A trigger might be a feature release, but the automation should stop and notify an owner when permissions widen, tests fail, an unknown repository appears, cost is abnormal, or public publication is required. Repetition does not remove judgment.
Related tutorials
[[zh]][[/zh]][[en]]Review a public website[[/en]]
SearchScope SEO/GEO
[[zh]][[/zh]][[en]]Access and usage guide[[/en]]
AI Prompt Management System | 418 Bilingual Prompts for Writing, SEO and AI Creation
High-Frequency AI Prompts for Work, Learning, and Teaching guide
High-Frequency AI Prompts for Work, Learning, and Teaching
Related reading
GitHub Copilot Can Generate and Edit Images: Check Cost, Watermarks, and File Output First
GitHub introduced a public preview for generating and editing images in Copilot on October 28, 2026. A user can describe an asset in VS Code, the GitHub Copilot app, or Copilot CLI. The selected reasoning model calls a dedicated tool powered by GPT Image 2.5 Flare, previews the result inline, and saves it into the project. The preview is available to Pro, Pro+, Business, and Enterprise plans. Image tokens are billed separately from the chat model against AI credits, and the visible “Made with AI” watermark is optional and off by default. This guide provides a bounded asset test covering input, output location, review, disclosure, and cost evidence.
GitHub Copilot Cloud Sessions Are GA: How Cross-Device Work Uses Actions Entitlement
GitHub made its connected Copilot cloud experience and cloud sandboxes generally available on paid Copilot plans on October 28, 2026. A user can start a task on github.com, GitHub Mobile, Copilot CLI, the Copilot app, VS Code, Slack, or Microsoft Teams, then continue the same session elsewhere. The included Actions compute entitlement becomes one shared, dollar-based pool for standard hosted runners, cloud sandboxes, and certain larger runners. Billing for cloud-sandbox usage begins in November 2026, so cross-device convenience can affect the same budget used by builds. This article helps users check repository scope, write access, tool permissions, entitlement consumption, and stop conditions before their first cloud session.
GitHub Copilot Repository Plugin Defaults Are GA: Prevent Permission Drift Across Teams
GitHub made repository plugin defaults and enterprise-managed plugin controls generally available in VS Code, Copilot CLI, and the GitHub Copilot app on October 28, 2026. A maintainer can define a marketplace and default plugins for a trusted repository so contributors avoid repeating setup. Enterprise administrators can require or block plugins and restrict installation to approved marketplaces. Managed settings take precedence over repository and personal choices, and a required plugin cannot be disabled by the user. This article gives teams a rollout checklist for validating publisher identity, plugin contents, MCP connections, credentials, uninstall behavior, repository trust, and the difference between a convenient default and a mandatory enterprise control.
From Chat Boxes to Personal AI Companions: AI Assistants Are Entering the Desktop Execution Era
AI assistants are moving from answering questions toward continuing real tasks. AI agents, MCP tool ecosystems, personal memory, and local workbenches are pushing this shift together. For users, the real value is not another chat box, but less repeated context setup and more continuity from thinking to doing.
VS Code Agent Host Runs in the Background: Choose Phone Control, Local Machines, or Cloud Sessions
GitHub announced its VS Code Copilot Universe release on October 28, 2026. The new Agent Host lets sessions continue after a project folder or editor window closes, can run on another machine through Remote SSH or dev tunnels, and can be directed from GitHub Mobile. A local or remote machine and its Agent Host must remain running when the work executes there. Computer use is experimental and requires approval for each application. The open Agent Host Protocol lets custom clients reconnect to the same live session. This article compares local, remote, and cloud placement, then provides a first-run checklist for availability, permissions, desktop access, and recovery.
GitHub Issue Artifacts Preview: What Agent Outputs Can Store and How Version History Works
GitHub announced Issue Artifacts in public preview on October 28, 2026. Teams can attach agent-generated plans, research, links, visualizations, and interactive HTML directly to an issue. Updates made on github.com retain version history as an artifact changes. GitHub CLI adds gh issue artifact commands to create, edit, list, view, download, and delete artifacts, while Markdown artifacts can include image and video attachments. This explainer uses a root-cause-analysis example to show which outputs belong beside an issue, how to separate observed evidence from unverified conclusions, when history helps reviewers follow a decision, and when an incorrect or sensitive artifact should be corrected or removed rather than being treated as repository truth.