Cursor 3.7: Canvases get Design Mode, context usage explorer, and better sharing
Cursor 3.7 expands Canvases with Design Mode (visual element annotation), an interactive context usage explorer, and improved canvas sharing and customization.
Editorial Team
The Authority AI Tools editorial team maintains this directory using vendor documentation, dated source checks, product changelogs, and clearly identified hands-on observations where available.
Cursor’s latest changelog entry (labeled 3.7) is centered on Canvases: interactive artifacts created by agents (dashboards, reports, internal tools) that you can share with teammates. (https://cursor.com/changelog)
The AI-native code editor with $1B+ ARR, 25+ models, and background agents on dedicated VMs
Design Mode: point at UI elements instead of describing them
Cursor added Design Mode to canvases, which lets you select and annotate UI elements directly to guide the agent’s edits — similar to giving feedback in a browser-based editor rather than translating everything into text. (cursor.com/changelog">https://cursor.com/changelog)
This is especially useful for UI-heavy work (layout tweaks, component spacing, chart formatting) where “change X to look like Y” is slower than pointing at the exact element.
Context usage explorer (as a canvas)
Cursor can now generate an interactive context usage report inside a canvas. It breaks down token usage across major buckets like the system prompt, tool definitions, rules, and skills, and because it’s a canvas you can ask follow-up questions to refine the report. (https://cursor.com/changelog)
Cursor also adds a “Debug with Agent” button to help identify opportunities to reduce context usage in a new conversation. (https://cursor.com/changelog)
Sharing + canvas quality-of-life improvements
Cursor’s changelog also calls out:
- Shared canvases can be opened full-screen in the browser (useful for presenting). (https://cursor.com/changelog)
- Agents can embed buttons in canvases that run a specific prompt when clicked. (https://cursor.com/changelog)
- Improvements to canvas type-error fixing, component styling, and chart customization. (https://cursor.com/changelog)
Source
- Cursor — “What’s New in Cursor”: https://cursor.com/changelog
Tools Mentioned in This Article
Free Resource
2026 AI Coding Tools Comparison Chart
Side-by-side comparison of features, pricing, and capabilities for every major AI coding tool.
No spam, unsubscribe anytime.
Workflow Resources
Cookbook
AI-Powered Code Review & Quality
Automate code review and enforce quality standards using AI-powered tools and agentic workflows.
Cookbook
Building AI-Powered Applications
Build applications powered by LLMs, RAG, and AI agents using Claude Code, Cursor, and modern AI frameworks.
Cookbook
Building APIs & Backends with AI Agents
Design and build robust APIs and backend services with AI coding agents, from REST to GraphQL.
Cookbook
Debugging with AI Agents
Systematically debug complex issues using AI coding agents with structured workflows and MCP integrations.
MCP Server
AWS MCP Server
Interact with AWS services including S3, Lambda, CloudWatch, and ECS from your AI coding assistant.
MCP Server
Context7 MCP Server
Fetch up-to-date library documentation and code examples directly into your AI coding assistant.
MCP Server
Docker MCP Server
Manage Docker containers, images, and builds directly from your AI coding assistant.
MCP Server
Figma MCP Server
Access Figma designs, extract design tokens, and generate code from your design files.
Frequently Asked Questions
What is Cursor 3.7: Canvases get Design Mode, context usage explorer, and better sharing?
Related Articles
Warp 2026.07.16 adds a cloud-agent connection indicator and more Agent Mode polish
Warp’s July 16, 2026 update adds a connection indicator for cloud agent sessions plus several Agent Mode and UI improvements.
Read more →Product UpdatesChatGPT (July 2026): global search across chats/projects/files + 5,000-character custom instructions
OpenAI’s mid-July 2026 release notes add global search across chats, projects, images, and documents, and expand custom instructions to 5,000 characters for paid plans.
Read more →Product UpdatesGoogle Antigravity CLI 1.1 adds code search, execution modes, and stronger diff review
Google’s Antigravity CLI changelog highlights new execution modes, line-level diff review, agent selection at launch, and a new /codesearch command, plus performance and reliability fixes.
Read more →