---
title: "Three types of agents, and why the middle one does the work"
description: "Knowledge agents, work agents and autonomous agents. Why the autonomous dream often derails today, and where the real gain is for those starting now."
language: en
source: https://coachsteff.live/en/drie-soorten-agents
---

# Three types of agents, and why the middle one does the work

The word agent comes up in every presentation about AI these days. Everyone has one, everyone is building one, and everyone means something different by it. In my workshops, I therefore make a simple distinction first. There are three types of agents, and they differ mainly in how much they do independently.

## From answering to acting independently

I call the first type the knowledge agent. It only responds when you ask something, in a chat window. You give it instructions and sources, for example your house style or your product information, and it answers within that framework. Handy, but it does nothing on its own.

The second type is the work agent. It can be triggered by something other than your question: a time, a date, a new email, a card you move on a board. It carries out a series of steps, uses tools, and delivers a result. An overview of your mailbox every morning, a report every Friday, every new quote neatly filed.

The third type is the autonomous agent. It gets a continuous role, runs in the background and decides for itself when it does what. That is the agent from the visions of the future: a digital colleague who is always on.