Blog

Run Modes control how the Cursor agent runs tool calls, and when Cursor interrupts you for approval.

AI can behave unexpectedly due to prompt injection, hallucinations, and other issues. We protect users with guardrails that limit what agents can do. By default, sensitive actions require your manual

Direct Agent with text prompts in the chat input. You can attach context, images, and voice, and switch models at any point.

Plan Mode creates detailed implementation plans before writing any code. Agent researches your codebase, asks clarifying questions, and generates a reviewable plan you can edit before building.

Agent is Cursor's assistant that can complete complex coding tasks independently, run terminal commands, and edit code. Access in sidepane with Cmd+I.

Design Mode lets you direct agents with visual prompts. From the browser in the Agents Window, you can click an element, draw on the page, or describe a change by voice. Cursor captures the context it

Debug Mode helps you find root causes and fix tricky bugs that are hard to reproduce or understand. Instead of immediately writing code, the agent generates hypotheses, adds log statements, and uses r

The Agents Window is Cursor's agent first interface. It provides a unified workspace to build with agents across repos and environments, including local, cloud, remote SSH, and more. It combines the p

Agent Review runs a dedicated code review on your local changes from inside Cursor.

Cursor has three update channels.