Skip to course content
Free agentic AI fundamentals course

Introduction to Agentic AI and Workflow Automation

Module 03

Tools, Permissions, and Safe Action Boundaries

By the end of this module you can decide what an agent is allowed to do, and design each permission so the worst-case action is one you could undo.

Units

  1. Unit 03.00: Sorting actions by whether you could undo them
  2. Unit 03.01: Giving an agent the narrowest tool that works
  3. Unit 03.02: Validating what the agent asked for
  4. Unit 03.03: Actions that must not run twice
  5. Unit 03.04: The permission list as a document you can audit

Module work