Skip to main content
AI News & Updates

@GitHub Is GA in Slack and Teams: How to Validate Canvas and Work Attribution

Conversations can start investigations, issues, changes, and pull requests; Teams Canvas supports side-by-side review and created work records the originating conversation and username

ENHE AI5 min6 views

GitHub announced on 2026-11-06 that @GitHub in Slack and Microsoft Teams is generally available. Teams can investigate bugs, create issues, implement changes, and open pull requests from a conversation. Teams Canvas adds a side-by-side place to review plans, code changes, and previews, while issues and pull requests created by @GitHub now record that they came from a Slack or Teams conversation and include the username. This guide provides a controlled first run: start with a read-only investigation, confirm the repository and permissions, inspect the plan and diff in Canvas, verify attribution on the created work item, require tests and code-owner review, and keep merge and deployment outside the chat task.

More topic tags (7)
AI NewsAuto PublishingSEOPR评论GitHub Slack Teams GA@GitHub CanvasSlack Teams Copilot
@GitHub Is GA in Slack and Teams: How to Validate Canvas and Work Attribution

Key takeaways

@GitHub can investigate bugs, create issues, implement changes, and open pull requests from Slack and Teams conversations.
Teams Canvas can show plans, code changes, and previews side by side, but human review remains necessary.
Created issues and pull requests record the source conversation and username; attribution does not prove correctness or approval.

By ENHE AI · 2026-11-09 · AI-assisted drafting and editorial checks.

Direct answer: general availability does not mean automatic deployment

@GitHub can turn a conversation into an investigation, issue, code change, or pull request, but those remain different states. General availability changes the product status; it does not make every generated change correct, merged, or deployed.

For the first acceptance test, choose a shareable, reproducible, low-risk problem and request read-only analysis first. Do not paste secrets, customer records, or complete production logs into chat.

Canvas, repository detection, and attribution in GA

Teams Canvas lets participants review implementation plans, code changes, and previews beside the conversation and continue discussing them. @GitHub can also identify a repository from the message to reduce repeated selection, but the detected repository still needs confirmation.

Issues and pull requests created by @GitHub record the Slack or Teams conversation and username. This helps trace the entry point, but it does not replace commit authorship, review records, tests, or approval.

A phone and laptop in a meeting represent chat-to-pull-request handoff. Contextual stock photo, not an actual conversation or repository record. Image: Unsplash.
A phone and laptop in a meeting represent chat-to-pull-request handoff. Contextual stock photo, not an actual conversation or repository record. Image: Unsplash.

Input and expected result for the first task

Example: “@GitHub Investigate the pagination error after filtering in org/site, read-only. List reproduction, relevant files, evidence, and unknowns first. Do not edit, create a pull request, or deploy.” Replace the repository with one you are authorized to use.

The expected result is not “fixed.” It is a reviewable plan in Canvas or the conversation: scope, files inspected, evidence, hypotheses, proposed files, tests, and risks. Missing access should produce an explicit limitation.

Acceptance from plan to pull request

After accepting the plan, separately authorize the smallest change and tests. Check that Canvas shows only allowed files, tests actually ran, the pull request contains source attribution, and branch protection and code-owner review still apply.

An issue records work, a pull request proposes code, a merge accepts it, and deployment changes live state. A completion sentence in chat cannot collapse those four stages.

Failure, permissions, and rollback

If the wrong repository is detected, reading exceeds scope, the diff is too broad, or tests fail, stop later actions, remove unnecessary access, preserve minimal failure evidence, and return to read-only investigation. Do not widen repository permissions to manufacture success.

Existing coverage of previews, multi-repository conversations, and Teams notifications provides background. This article covers only the November 6 GA, Canvas, and attribution changes rather than recreating an older event.

FAQ

Is a plan in Canvas automatically approved?

No. Canvas supports shared review; approval still depends on team roles, code review, and branch protection.

Does source attribution prove the change is correct?

No. Attribution records the entry point and username. The diff, tests, permissions, and review remain separate evidence.

Related tools and reading

These pages support the same task, workflow, or decision boundary.

Conclusion

Start with a read-only investigation and treat conversation, plan, diff, test, pull request, merge, and deployment as different states. Continue only when repository scope, attribution, tests, and human review are clear.

What this means for everyday users

After accepting the plan, separately authorize the smallest change and tests. Check that Canvas shows only allowed files, tests actually ran, the pull request contains source attribution, and branch protection and code-owner review still apply.

Related reading

How to Adopt AI Agents in Slack and Teams with an Approval Checklist

Review the official scope, availability, ordinary-user task, permissions, cost, review, and rollback checks for How to Adopt AI Agents in Slack and Teams with an Approval Checklist.

GitHub in Slack and Teams Adds Multi-Repository Work in One Conversation

GitHub’s Slack and Teams integration can now work across multiple repositories within a single conversation. That is useful when a reported problem spans a frontend and backend, but it is a different event from the original launch of the chat integrations. This article explains the change and provides a scoped investigation request that a non-programmer project owner can give a technical collaborator. It describes what evidence to request before moving from analysis to code changes and how to distinguish an issue, a proposed pull request, a merge, and a deployment. No account-level availability test or automatic resolution is claimed, and the announcement is not treated as permission to change every repository.

GitHub Copilot in Teams Turns Notifications Into Pull Requests: What to Check Before Review

GitHub updated its Microsoft Teams app on October 23, 2026, so an issue notification in a channel, group chat, or private chat can become a Copilot task that investigates the problem, proposes a fix, and opens a pull request. This article helps development and product teams adopt the workflow without mistaking an automated pull request for shipped code. It explains the consolidated app, repository connection, the November 16 retirement of the legacy GitHub app, and the review boundary. A practical acceptance checklist asks teams to reproduce the issue, inspect changed files, run targeted tests, verify permissions, and keep merge and deployment as explicit human decisions.

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.

ChatGPT Adds an Accounting Plugin: Keep Source, Variance, and Approval Tables for Month-End Work

OpenAI announced the ChatGPT Accounting plugin on November 18, 2026. It can help reconcile transactions, draft invoice entries, and prepare month-end reports from records and templates, while Enterprise workspaces still require administrator approval before installation. This article does not provide personalized accounting or financial advice. Instead, it supplies three control tables: a source table for files, periods, and versions; a variance table for every unmatched amount; and an approval table that names who may confirm, export, or roll back a change. Bank access, payments, credentials, and final posting remain human-reviewed steps. The plugin output is a reviewable draft, not a closed accounting period or evidence that the underlying records are complete.

GitHub Copilot Evals Enters Preview: Regression-Test Skills, Agents, and MCP Changes

GitHub launched Copilot Evals in public preview on November 17, 2026. It creates repeatable tests for skills, custom agents, and MCP tools and lets users compare runs before and after a customization change. This guide defines a minimum regression set: choose three realistic tasks, then specify the input, allowed tools, success criteria, and prohibited behavior for each. Preserve at least one baseline run and one post-change run, including the result, execution path, failed checks, and human review. Merge a customization only when the change preserves the original task, permission boundary, and evidence chain. A single passing answer is not enough because model output can vary, and an automated check cannot decide every domain-specific quality or safety question.