# Permission request

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

Also called: permission prompt, approval prompt, allow or deny, tool approval, approve action

The pause where an [agent](https://ecosystem.samcarlton.com/ai-agent) asks before it takes an action its [permission mode](https://ecosystem.samcarlton.com/permission-mode) does not allow on its own. You approve or decline, and the agent carries on with that answer.

**For example:** The [agent](https://ecosystem.samcarlton.com/ai-agent) asks to run a command that resets the test [database](https://ecosystem.samcarlton.com/database). The [founder](https://ecosystem.samcarlton.com/founder) declines because the command is pointed at live [customer data](https://ecosystem.samcarlton.com/data-privacy).

## Connects to (5)

- [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.
- [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.
- [Tool use](https://ecosystem.samcarlton.com/tool-use): A way for a model to ask the software around it to run a defined action, such as a search or a database lookup, and send back the result.
- [Agent mode](https://ecosystem.samcarlton.com/agent-mode): A named setting in a coding agent that changes how freely it acts.
- [Production](https://ecosystem.samcarlton.com/production): The live version of your app that real customers use.

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