Skip to content
BENIBIX Learn

Agent Permissions

AI🤖 AI AgentsAgent Control

Also known as Agent Allow List, Tool Permissions, Permission Mode

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

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.

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.

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.
Each action falls in one list: allowed, ask first or denied. The harness checks it every time.

Common mistake

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

Key takeaways

  1. 1
    Allow, ask or deny. Three answers.
  2. 2
    Checked before each action. By the harness.
  3. 3
    Least access. Only what the task needs.

Compare