# Permission mode

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

Also called: permission settings, approval mode, auto-approve, allowlist, allow list

The rules that decide which actions an [agent](https://ecosystem.samcarlton.com/ai-agent) may take on its own and which need your approval first. Stricter rules are safer but interrupt you more. Looser rules let it work unattended and should be paired with a [sandbox](https://ecosystem.samcarlton.com/sandbox).

**For example:** A team lets its [agent](https://ecosystem.samcarlton.com/ai-agent) read any file freely but requires approval before it deletes files or runs anything that reaches the internet.

## Connects to (7)

- [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.
- [Agent mode](https://ecosystem.samcarlton.com/agent-mode): A named setting in a coding agent that changes how freely it acts.
- [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…
- [Human in the loop](https://ecosystem.samcarlton.com/human-in-the-loop): Designing an AI process so a person reviews, approves or corrects the AI's work at key steps instead of letting it act alone.
- [AFK](https://ecosystem.samcarlton.com/afk): Short for away from keyboard.
- [Harness](https://ecosystem.samcarlton.com/harness): The software wrapped around an AI model that turns it into a working agent.
- [Guardrails](https://ecosystem.samcarlton.com/guardrails): Checks and limits built around a model inside a product.

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