By the end of this lesson, you should be able to explain what makes an AI system agentic, identify the core loop of perception–reasoning–action, and distinguish agentic systems from static model responses.

A normal language model responds to a prompt. An agentic system uses the model as one component inside a larger control loop. That loop may include planning, tool use, memory, environment feedback, and retry logic. The key distinction is that the system is tasked with doing something, not only saying something.

A common abstraction is: $$\text{observe} \rightarrow \text{plan} \rightarrow \text{act} \rightarrow \text{evaluate} \rightarrow \text{repeat}$$. Each cycle narrows uncertainty and moves the system closer to a target outcome.