AI agent: definition

An AI agent is a system that uses a language model to decide which steps to take and which tools to call to finish a goal, instead of just answering a single prompt.

A plain chatbot answers one question at a time. An agent is given a goal, like "book the site visit and update the CRM," and it loops: it reasons about what to do next, calls a tool (search, an API, a database), reads the result, and decides the next move until the job is done.

The useful mental model is an employee you can hand a checklist to, not a search box. The risk is the same as with a new hire: it needs clear boundaries, the right tools, and a human to escalate to when it is unsure. Most of the systems we ship are narrow agents with two or three tools and a hard handoff rule, because that is what actually survives contact with real customers.

Related terms

Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.
Model Context Protocol (MCP): The Model Context Protocol is an open standard that lets an AI model connect to external tools and data sources through one consistent interface, instead of a custom integration for each one.
Workflow automation: Workflow automation is the practice of moving a repeatable business process from manual steps to a system that runs it end to end, with a person involved only where judgement is actually needed.
Human in the loop: Human in the loop is a design where an AI system does the work but a person reviews, approves, or handles the cases the system is unsure about, keeping judgement and accountability with a human.