Foundations
Agent
An LLM given tools and a goal, which takes multiple steps on its own rather than answering a single question.
A chatbot answers. An agent acts.
Given a goal like "file this shipment", an agent decides which steps to take, calls real functions in your systems to take them, reads the results, and corrects course. The model is not doing the work directly — it is choosing which of your tools to call and with what arguments.
This is a genuine category change, and it is also where the risk lives. A system that can only read is a search box. A system that can write can create records, spend money and email customers. That is why production agents need approval gates enforced in your backend rather than requested in a prompt.