# Agent mode

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: plan mode, accept edits, auto-accept, bypass permissions, YOLO mode, yolo, ask mode, agent modes

A named setting in a [coding agent](https://ecosystem.samcarlton.com/coding-agent) that changes how freely it acts. Examples include a plan-only mode that proposes changes without making them, and a mode that skips [permission prompts](https://ecosystem.samcarlton.com/permission-request). Each mode pairs a permission level with [instructions](https://ecosystem.samcarlton.com/prompt) about how to behave, and you can usually switch partway through a [session](https://ecosystem.samcarlton.com/session).

**For example:** A [founder](https://ecosystem.samcarlton.com/founder) starts in plan mode to agree on an approach, then switches to a mode that lets the [agent](https://ecosystem.samcarlton.com/ai-agent) edit files without asking every time.

## Connects to (6)

- [Permission mode](https://ecosystem.samcarlton.com/permission-mode): The rules that decide which actions an agent may take on its own and which need your approval first.
- [Permission request](https://ecosystem.samcarlton.com/permission-request): The pause where an agent asks before it takes an action its permission mode does not allow on its own.
- [Coding agent](https://ecosystem.samcarlton.com/coding-agent): An AI agent that writes and changes code.
- [Sandbox](https://ecosystem.samcarlton.com/sandbox): A walled-off space where an agent can run commands and change files without reaching the rest of your computer, your accounts or the open…
- [AFK](https://ecosystem.samcarlton.com/afk): Short for away from keyboard.
- [System prompt](https://ecosystem.samcarlton.com/system-prompt): Standing instructions that the builder of an AI product gives the model before any user types.

Map view: https://ecosystem.samcarlton.com/agent-mode