# Agent Permissions

> Rules for an agent. They say what it can do alone, what it must ask about, and what it can't do.

**Field:** Artificial Intelligence  
**Category:** AI Agents  
**Also known as:** Agent Allow List, Tool Permissions, Permission Mode

## Think of it like

Think of it like house rules for a guest. Some rooms are open, some need a knock, and some are locked.

## Definition

Agent permissions are rules that say what an agent may do on its own. They also say what needs a person's yes, and what is never allowed. Rules are often set per tool or per command. For example, it may read files, must ask before it edits them and may never touch secret keys. The harness checks each action against the rules before it runs. Tight rules lower the risk, and loose ones mean fewer stops.

## Example

Emma lets her coding agent read any file and run the tests on its own. It must ask before it edits code, and it can never read the passwords file.

## Why it matters

An agent acts fast. Permissions decide which of its mistakes are possible at all.

## Common mistake

Turning on 'allow everything' to stop the questions. That removes the one check between a bad step and real damage.

## Three principles

- **Allow, ask or deny.** Three answers.
- **Checked before each action.** By the harness.
- **Least access.** Only what the task needs.

## Related terms

- [Human-in-the-Loop](https://learn.benibix.com/term/ai/human-in-the-loop)
- [Agent Sandbox](https://learn.benibix.com/term/ai/agent-sandbox)
- [Agent Harness](https://learn.benibix.com/term/ai/agent-harness)
- [Principle of Least Privilege](https://learn.benibix.com/term/development/principle-of-least-privilege)
- [Agent Autonomy](https://learn.benibix.com/term/ai/agent-autonomy)

## Told apart from

- [Agent Sandbox vs Agent Permissions](https://learn.benibix.com/compare/agent-sandbox-vs-agent-permissions): People often think that if an agent has strict permissions, it does not need a sandbox. Permissions decide which actions the agent may take, and they depend on each action being checked. A sandbox limits what any action can reach, even one that slipped through. Permissions stop the wrong step. A sandbox keeps the damage small when one gets past.

![Three lists of actions. Allowed: read files, run tests. Ask first: edit files. Denied: read secrets, delete the database.](https://learn.benibix.com/diagrams/ag-agent-permissions.svg)

---

Source: https://learn.benibix.com/term/ai/agent-permissions
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
