This course contains the use of artificial intelligence.

AI agents are everywhere in the headlines — but what are they actually, and how do they really work? This course pulls back the curtain on autonomous AI systems, breaking down the exact architecture that lets AI go beyond simple chat responses and take real, independent action.

You'll start with the fundamentals: what makes something an 'agent' versus a chatbot, and where you've likely already encountered agents in products you use daily. From there, you'll dive into the core perceive-think-act loop, learn how large language models function as an agent's reasoning brain, and understand how goals and system prompts shape behavior.

Next, you'll explore how agents remember — from short-term context windows to long-term memory using vector databases — and how they decide what information to keep or discard. You'll then learn how agents interact with the world through function calling and tool selection, and how they chain multiple actions together to complete complex, multi-step tasks.

Finally, you'll examine advanced concepts like planning, task decomposition, and self-correction, along with a clear-eyed look at the real limitations, risks, and safety concerns surrounding today's agentic AI systems.

By the end, you won't just understand the buzzwords — you'll be able to explain, evaluate, and reason about AI agents with genuine technical clarity, whether you're a curious learner, a builder, or a decision-maker navigating this fast-moving space.