At GitHub Universe on Oct 28, GitHub shipped a batch of Copilot Automations updates. Shared automations now belong to the repository, act as Copilot, bill AI credits to the repo owner and keep running after their creator leaves. Automations gain 24 new GitHub event triggers, REST API triggers from external systems and chaining, plus 20 new tools and custom MCP servers. Teams can cap AI credits per run, day, week or month, automations can propose improvements to their own prompts from real outcomes, and VS Code 1.144 can run them in the cloud.
Key Takeaways
- ✓Shared automations belong to the repository: anyone with read access can view them, anyone with write access can edit, actions are attributed to Copilot and AI credits bill to the repo owner
- ✓24 new triggers across issues, pull requests, discussions and security alerts, plus REST API triggers from systems like Jira, Sentry and PagerDuty
- ✓20 new GitHub tools (merge PRs, retry workflow runs, upload screenshots and more) and support for custom MCP servers
- ✓AI credit limits can be set per run, day, week or month; org repos need an admin to enable the "Allow use of Copilot cloud agent billed to the organization" policy
- ✓Rolling out to Copilot Pro, Pro+, Max, Business and Enterprise; VS Code 1.144 runs them in the cloud with chat.automations.cloud.enabled
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background and pain point
More teams now hand issue triage, code review and incident investigation to AI agents that run on a schedule or on events. Until now, Copilot Automations were personal: only the creator could see or edit them, and they ran with the creator's identity and AI credits. When that person left or changed teams, the workflow broke, and costs landed on an individual. On Oct 28, day one of GitHub Universe, GitHub's changelog and the @github account announced a set of updates that turn automations into team assets.
How it works
Shared automations belong to the repository. Anyone with read access can see them and anyone with write access can edit them; actions on GitHub are attributed to Copilot, AI credits bill to the repository owner, and change history is kept. Automations gain 24 new event triggers across issues, pull requests, discussions, and code scanning, secret scanning and Dependabot alerts. They can also be started from external systems through the REST API and chained into multi-step workflows with run succeeded or failed triggers. There are 20 new GitHub tools and support for custom MCP servers. Self-improvement uses real signals, such as whether people change applied labels, accept review comments or merge the PRs an automation opens, to propose prompt changes that a person reviews before they apply.
Benchmarks and results
This is a product feature update. GitHub has not published quality or cost comparisons.
For developers
When creating an automation on github.com, in the GitHub Copilot app or in VS Code, choose Shared under Type (the type can't be changed later). Organization repos need an admin to enable the "Allow use of Copilot cloud agent billed to the organization" policy. Set per-run and monthly AI credit limits first, start with low-risk jobs like reproducing bugs from new issues or capturing PR screenshots, and hold back high-privilege tools such as merging PRs until the workflow is stable.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.