Action Restrictions and Permissions › When to Use Each Technique

Michael BrenndoerferAugust 14, 20251 min read
AI Agent HandbookAll chapters
Part 13 of 15Safety and Governance - Keeping the Agent Aligned
Chapter 37Action Restrictions and Permissions › When to Use Each Technique
Reading section 9 of 11 · When to Use Each Technique · 1 minSection 9 of 11 · 1 min

Book contents

Section 9 of 11 · 1 min read

Action Restrictions and Permissions › When to Use Each TechniqueOne section · Sections in this chapter9 / 11 ↓

Different situations call for different approaches:

Use permissions when you want to completely disable certain capabilities. If your agent should never send emails, don't give it the permission.

Use restrictions when you want to limit the scope of allowed actions. The agent can send emails, but only to certain people.

Use confirmations when actions are risky but sometimes necessary. The agent can delete files, but only after you approve each deletion.

Use sandboxing when you need strong isolation. If your agent runs untrusted code or processes user-uploaded files, put it in a sandbox.

For our personal assistant, here's a reasonable configuration:

  • Permissions: Read files, send emails, make API calls (no delete, no system commands)
  • Restrictions: Only read from designated folders, only email known contacts
  • Confirmations: Required for sending emails, making purchases, posting publicly
  • Sandboxing: Not needed for basic assistant tasks, but useful if adding code execution

This gives the agent enough power to be useful while keeping risks manageable.