Demos run a short happy path once with a human watching. Production runs thousands of variations unattended, where per-step error rates compound and an unbounded permission scope turns a wrong decision into an incident. The deployments that work narrow the scope, verify each step cheaply, and gate every irreversible action.
An AI agent is a language model that has been given tools it can call, a goal to pursue, and permission to take several steps without asking a human between each one. A chatbot answers a question and stops; an agent keeps acting until it decides the goal is met or it runs out of budget.