Concept · Building with AI
Permission mode
Also called: permission settings, approval mode, auto-approve, allowlist, allow list
The rules that decide which actions an 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.
For example: A team lets its agent read any file freely but requires approval before it deletes files or runs anything that reaches the internet.
Connects to 7
- Permission request Concept
- Agent mode Concept
- Sandbox Concept
- Human in the loop Concept
- AFK Concept
- Harness Concept
- Guardrails Concept