An AI agent's ability to directly control a computer — moving a mouse, clicking, and typing — by looking at screenshots, rather than only interacting through an API.
This lets an agent operate regular software built for humans, including apps and websites that were never designed with AI access in mind.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →