AI agents
From answering questions to completing missions.
The analogy
A chatbot is like an expert on the phone: they can answer you, but they can't do anything for you. An agent is like an assistant with their own computer: they plan, search, use programs, fix their own mistakes, and come back when the job is done.
In detail
An agent is an LLM running in a loop with access to tools (web search, code execution, file reading…). It receives a goal, breaks it into steps, acts, observes the result and decides the next step until the goal is met. Protocols like MCP make it easy to connect it to more tools.
An example
You ask: “find the three cheapest flights to Rome in March and build me a comparison table”. The agent searches several sites, extracts the prices, compares them and hands you the table.