Cursor is an AI-native code editor built as a fork of VS Code, designed from the ground up for AI-assisted development. Unlike traditional editors with AI plugins, Cursor integrates autonomous agents, multi-file editing, and context-aware autocomplete directly into every workflow. It supports all major programming languages, VS Code extensions, and connects to frontier models from OpenAI, Anthropic, Google, and others. The key mental model: Cursor doesn't just suggest code—it can write, review, debug, and refactor entire features autonomously while you maintain full control through a diff-based review interface.
What This Cheat Sheet Covers
This topic spans 14 focused tables and 101 indexed concepts. Below is a complete table-by-table outline of this topic, spanning foundational concepts through advanced details.
Table 1: Core AI Features
| Feature | Example | Description |
|---|---|---|
Type def calculate_ and Tab autocompletes:def calculate_total(items): return sum(item.price for item in items) | • AI-powered autocomplete predicting multi-line code blocks from project context • accepts with Tab, rejects with Esc • learns from your accept/reject patterns | |
Select code, press Cmd+K, type "add error handling"AI edits selection in-place | • AI code modification triggered by keyboard shortcut • works on selected code or at cursor position without opening chat | |
Press Cmd+L, ask "How does authentication work?"AI explains code with context | • Conversational assistant for questions, explanations, and brainstorming • maintains chat history; reference files and symbols with @ mentions | |
Press Cmd+I, prompt "Add user registration feature"AI creates routes, models, views across files | • Multi-file editing agent that plans and executes changes across the codebase • creates, modifies, and deletes files; shows diff preview before applying | |
Drag a UI mockup screenshot into Chat — AI generates matching code | • Accepts images as context: drag-and-drop screenshots, design mockups, or error dialogs directly into Chat or Composer • model understands visuals |