AIToday
Large Language ModelsAI Coding AssistantsGitHub Copilot BlogPublished: Sep 26, 2026, 04:00 JST

GitHub Copilot app adds canvases for custom workflows

GitHub Copilot app adds canvases for custom workflows

3 Key Points

  1. What happened

    GitHub detailed canvases—custom interfaces built via the /create-canvas skill—where users describe the workflow, controls, and agent actions in plain English and the agent generates the UI.

  2. Why it matters

    Canvases are bidirectional, so the agent and user update the same shared state without send or sync steps, potentially cutting time spent adapting work to fixed tool layouts.

  3. What to watch

    The approach hinges on whether agent-generated interfaces stay stable as workflows evolve; ready-made extensions are available on Awesome Copilot for users who want a starting point.

WHO IT HITSProduct managers, designers, and other non-engineering team members who use GitHub Copilot app could build and share custom boards or checklists without coding, though the post frames it as a beginner tutorial rather than a full release announcement.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

The post is written as a beginner tutorial, positioning canvases as a shift away from fixed tool layouts. Most tools give a fixed set of screens and ask users to fit work into them; canvases invert that by starting with the workflow and generating the interface around it. GitHub describes the canvas as bidirectional—the agent can update it as it works, and the user can use buttons, cards, and filters to make changes, like a live shared whiteboard.

Collaboration is a central theme. GitHub emphasizes that when a user clicks a button or moves a card, the shared state changes immediately and the agent sees the update without a separate sync step. The reverse also works: users can ask the agent to use the canvas's own capabilities to add a release note or move a card, then watch the change appear.

For teams, the practical takeaway may hinge on whether these generated interfaces hold up as workflows change. GitHub notes there is no fixed menu of layouts—if you can describe a workflow, you can likely turn it into a canvas—so the real test is whether iterating with the agent keeps the canvas useful over time. The post suggests starting small and refining from there, which may suit beginners more than teams with complex, stable processes.

FAQ
How do I create a canvas in GitHub Copilot app?
Open an agent session, enter the /create-canvas skill, and describe the workflow, the interface controls you want, and what the agent should be able to do in plain English. The agent then builds the interface and opens it in the right-side panel.
Can I share a canvas with my team?
Yes. A canvas is saved as an extension, so you can keep it with the project for your team to share or save it as a personal extension just for you.
Where can I find ready-made canvas extensions?
The community has shared ready-made extensions through Awesome Copilot, including release notes tools, kanban boards, and issue triage workflows.
GitHub Copilot BlogRead Original Article

Also reported by GitHub Blog (AI)

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Salesforce at Dreamforce 2026: UCLA Health hits 75,000+ AI chatsTop Companies AI · 2h ago
  • Kavukcuoglu: Gemini 4 hits post-training, early ship eyedTop Companies AI · 2h ago
  • CrowdStrike (CRWD) joins Blueprint Alliance for AI agent securityTop Companies AI · 2h ago

AI-summarized, only the topics you pick: one digest a day via Email, LINE, or Slack.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleGitHub Copilot app adds canvases for custom workflows