GitHub Blog

How to build interactive experiences with canvases

GitHub Copilot's canvas extensions are shared interactive surfaces that allow developers and agents to collaborate in real time. Unlike traditional conversational interfaces, canvases enable direct manipulation of information—such as swiping through issues, visualizing code structure, or managing worktrees. Users can create canvases via a simple prompt and iteratively refine them. Examples include issue triage helpers, interactive codebase diagrams, session worktree views, agent prompt coaches, and knowledge finders. Canvases transform AI from a conversational tool into a visual, interactive workspace for exploration and action.

Statesummarized
Snapshots1
AI Outputs2
Open issues0

validated summary

English

How to build interactive experiences with canvases

GitHub Copilot's canvas extensions are shared interactive surfaces that allow developers and agents to collaborate in real time. Unlike traditional conversational interfaces, canvases enable direct manipulation of information—such as swiping through issues, visualizing code structure, or managing worktrees. Users can create canvases via a simple prompt and iteratively refine them. Examples include issue triage helpers, interactive codebase diagrams, session worktree views, agent prompt coaches, and knowledge finders. Canvases transform AI from a conversational tool into a visual, interactive workspace for exploration and action.

  • Canvases are shared interactive surfaces in GitHub Copilot app for real-time collaboration between developers and agents.
  • They enable direct interaction with information, avoiding long chains of prompts and responses.
  • Canvases can be created with a simple /create-canvas prompt and iteratively refined.
  • Examples include issue triage card swipe, interactive codebase diagrams, worktree visualization, prompt coaching, and cross-tool knowledge search.
  • Canvases turn AI from a conversational tool into a visual, interactive workspace.
  • The canvas evolves alongside the user's workflow, adding new functionality as requested.

Chinese

如何利用画布构建交互式体验

GitHub Copilot的画布扩展是共享交互界面,使开发者和代理能够实时协作。与传统对话式界面不同,画布允许直接操作信息——例如滑动浏览问题、可视化代码结构或管理工作树。用户可通过简单提示创建画布并迭代优化。示例包括问题分类助手、交互式代码库图、会话工作树视图、代理提示教练和知识查找器。画布将AI从对话工具转变为可视觉化、可交互的工作空间。

  • 画布是GitHub Copilot应用中的共享交互界面,支持开发者与代理实时协作。
  • 允许直接与信息交互,避免冗长的提示和响应链。
  • 可通过简单的/create-canvas提示创建画布,并不断迭代优化。
  • 示例包括问题滑动分类、交互式代码库图、工作树可视化、提示教练和多工具知识搜索。
  • 画布将AI从对话工具转变为可视化、交互式的工作空间。
  • 画布随用户工作流演进,按需添加新功能。

canvases / GitHub Copilot / interactive experiences / AI collaboration / visualization / developer tools / canvas extensions / prompt engineering / workflow automation

Full Article

Jacklyn Carroll · @jacklynlee31

July 21, 2026|

5 minutes

Share:Most developers are now working alongside agents, or are at least familiar with how to do so. Agents help you explore ideas and turn them into action, from planning projects to automating workflows. Oftentimes, a conversation is all you need to move your work forward.But what about tasks that don’t quite fit the conversation mold?Some tasks are easier when you can see and interact with the information. You may need to triage a backlog, visualize complex information, or bring information together from multiple sources. A visual interface makes it easier to understand patterns, spot connections, and take action.Instead of working through a long chain of prompts and responses, you can use canvases to interact directly with the information in front of you.Working with canvasesThese shared, interactive surfaces are extensions of the Copilot app called canvases. A canvas is an interface in the GitHub Copilot app where developers and agents can collaborate in real time. These shared, interactive surfaces are called canvas extensions.The agent can update the canvas as it works, and you can interact with that same workspace through clicks, edits, and other actions. Your interactions can be sent back to the agents  or  processed locally by the canvas.You can continuously shape the experience by asking Copilot to iterate on your canvas—adding new functionality, refining existing features, and more. The canvas can evolve alongside your work.To create a canvas, use  /create-canvas  in your agent session in the GitHub Copilot app, then describe what you want it to create and what capabilities it should be able to support.Because canvases are generated from a prompt and evolve alongside your workflow, they can take many forms. Some help you visualize information, some help you take action, others provide a more entertaining way to tackle your backlog.Here’s some examples of what’s possible with canvas extensions:Issue triage helperGoal : Quickly triage GitHub Issues in a fast, visual way.Prompt :  /create-canvas Create an interface that allows me to easily swipe through issues in a repo in card format. Can swipe right to ship, left to reject.Result : The canvas shows a card-based interface where each issue is surfaced one at a time. You can take action directly from the UI. As you swipe, the canvas updates in real time, tracking decisions and moving the items into the appropriate buckets.Interactive codebase diagramGoal : Visualize how a project is structured and how its components relate to each other.Prompt :  /create-canvas Render a colorful, interactive diagram showing how the code in this project is working together, show how things are related, etc.Result : The canvas generates a dynamic diagram of the codebase where each node represents a different part of the system. You can hover, drag, and filter to explore the different layers. You can interact with the architecture directly, turning a static understanding of a codebase into something you can actively explore.Sessions worktree viewGoal : Visualize all active GitHub Copilot app sessions and their associated git worktrees, clearly indicating which are active and which are stale, with the ability to easily clean things up where needed.Prompt :  /create-canvas Create a worktree view that will help me see all of my current sessions and whether or not they are active or orphaned. Allow me to clean them up with a few clicks where neededResult : The canvas generates a visual showing my worktrees with clear indication of what is active and what is currently stale or orphaned. I can clean up stale worktrees with the click of a button.Agent prompt coachGoal : Improve prompt quality by reviewing past interactions and suggesting clearer, more effective ways to work with agents.Prompt :  /create-canvas Create an interactive prompt coach that suggests to you how you could have improved your previous prompts in your sessions with skills, mcp servers, etc. Make note of any spelling errors, syntax errors, etc.Result : The canvas shows a list of previous prompts and analyzes each one, suggesting improvements such as missing context, spelling issues, and more. You can use these tips to refine your future prompts, improve clarity, and get more consistent results from the agent.Knowledge finderGoal : Find people who have context on a specific file or topic by searching across Slack, Teams, email, and documentation.Prompt :  /create-canvas Create a way that I can search across Slack, Teams, Email and docs to find people with knowledge of a specific file or someone that would have more context.Result : Based on the search, the canvas looks across multiple tools and surfaces the people that are most connected to a given file or subject. It highlights who the person is, and where the connection was found. This allows you to quickly understand someone’s connection to a topic and make it easier to reach out for more information.Take this with youThese examples only scratch the surface of what you can do with canvases. Canvases can turn AI from a conversational tool into a place where you can visualize information, explore different workflows, and turn boring tasks into fun experiences that you’ll actually want to complete.Canvases are a fun, shared workspace where you and the agent can think, explore, and take action together.Want to try out canvas extensions? You can get started in the  GitHub Copilot app .  Read the docs  for more information >Tags:

canvases

GitHub Copilot

GitHub Copilot appWritten byJacklyn Lee is a Content Writer at GitHub and a former technical writer with a love for good storytelling.Related postsAI & ML

Better tools made Copilot code review worse. Here’s how we actually improved it.How migrating Copilot code review to shared Unix-style code exploration tools reduced review cost by reshaping agent workflows around pull request evidence.AI & ML

Automating cross-repo documentation with GitHub Agentic WorkflowsExplore how the Aspire team turns merged product changes into SME-reviewed docs pull requests, closing the gap between release and documentation.AI & ML

How GitHub Copilot enables zero DNS configuration for GitHub PagesGo from an empty repository to a live custom domain with HTTPS in about 14 minutes, without manually editing a single DNS record.We do newsletters, tooDiscover tips, technical guides, and best practices in our biweekly newsletter just for devs.Your email address

Snapshots

Fetch evidence retained for parsing and audit.

200 · text/html; charset=UTF-8

07/22/2026, 08:00 AM

22971414944cb2c8f14266c5f543cdea11bf0a6c51f6fe888b09b23f024d819b

AI Outputs

Structured model outputs with validation status.

article.summarize

deepseek-v4-flash · valid

{"tags":["canvases","GitHub Copilot","interactive experiences","AI collaboration","visualization","developer tools","canvas extensions","prompt engineering","workflow automation"],"titleEn":"How to build interactive experiences with canvases","titleZh":"如何利用画布构建交互式体验","summaryEn"...
article.classify

deepseek-v4-flash · valid

{"relevant":true,"confidence":0.95,"primaryTopic":"agent-engineering","secondaryTopics":["software-engineering","product-updates"]}

Quality And Digest Links

Open and resolved issues, plus daily digest appearances.

digest

Signal Hub 2026-07-22

GitHub Copilot的画布将AI协作转变为开发者可视觉化、可交互的工作空间。 (score: 0.90)

position 207/22/2026, 12:00 AMdraft