An AI agent is a program that relies on a language model (LLM) to reach a goal in several steps: it decides which actions to take, uses tools (search, code execution, API calls, reading and writing files), observes the result and adjusts what comes next, with more or less human supervision.
The difference from a chatbot: a chatbot answers a question, an agent chains actions to complete a task. A coding agent, for example, can read a repository, edit files, run the tests and fix its own mistakes. The open MCP protocol (Model Context Protocol) is used to connect tools and data sources to these agents in a standard way.
Building a reliable agent is hard: you have to limit its permissions, add guardrails, measure the quality of its output and manage the cost and latency of many model calls.
Why it matters when hiring
Many profiles have put together an agent demo in a few days, few have put one into production. In interviews, ask how the agent was evaluated, what happened when it got things wrong and how its permissions were limited. This work belongs to the AI Engineer or Agent Engineer: a good back-end developer with real evaluation rigor is often stronger here than an ML researcher.