AI Agents
Systems where a model plans, uses tools, and acts over multiple steps.
An agent wraps a language model in a loop: it reasons about a goal, chooses an action (such as calling a tool, running code, or browsing), observes the result, and repeats until the task is done. This turns a one-shot responder into something that can carry out multi-step work.
Patterns like ReAct, tool use, and function calling are the foundations of the current wave of agentic products.