# What is an AI Agent

> Understand the core architecture of autonomous AI agents, including perception, planning, memory, and tool execution, and why they expand the attack surface.

Canonical: https://codelivly.com/rooms/what-is-an-ai-agent
Last updated: 2026-10-13

| | |
|---|---|
| Level | Advanced |
| Category | Cybersecurity |
| Lessons | 2 |
| Estimated time | 30 min |
| XP | 100 |

This module introduces the foundational architecture of autonomous AI agents and multi-agent systems. You will explore the transition from passive LLMs to active agents capable of reasoning, maintaining state, and executing multi-step workflows. Crucially, you will learn how this autonomy introduces complex trust boundaries and privilege escalation risks that traditional application security models cannot handle.

## Lessons

1. What is an AI Agent & How It Differs from a Chatbot (30 min)
2. Autonomous vs Assisted Agents (30 min)

## Related

- [Learning path: AI Agent Fundamentals and Trust Boundaries](https://codelivly.com/learning-paths/ai-agent-fundamentals-trust-boundaries)
- [All rooms](https://codelivly.com/rooms)