Agentic AI Basics

In this module of the AI Security learning path, you will watch agentic AI basics: a naive agent loop that picks tools from a natural-language goal. Personas are labels, not authorization. You will compare an arithmetic goal (no tool) with a file goal (read_workspace) on POST /agent/run. Upon completion of the module, students will be able to: - Describe an agent as goal, tool, observe, repeat. - Read an agent trace and identify the tool that ran. - Explain why a persona string is not an ACL. For inquiries, please write us at https://www.darkrelay.com/cybersecurity-course-inquiry