Computer Use: how AI agents operate software
Understand this story
In a November 19, 2026 article, the Browser Use Blog explained that Computer Use lets AI agents operate software like a person by clicking, typing, and scrolling, with the core being a loop of "read the interface—choose an action—execute—check the result." Agents read the interface mainly in three ways: screenshots, the DOM, and the accessibility tree. By target of operation, browser agents are aimed at websites, while desktop agents can also operate native applications.
AI overview based on source reports · Updated 18 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Browser Use BlogWhat Is Computer Use? How AI Agents Operate Software
Computer use lets AI agents operate software through its user interface by reading the screen, deciding on actions, and clicking, typing, or scrolling in a loop of reading the interface, choosing an action, carrying it out, and checking the result. Agents read interfaces via screenshots, the DOM, and accessibility trees, and can run in browsers or on desktops with native apps. The article covers use cases such as portals, legacy apps, cross-app workflows, and UI testing, and warns about mistakes, slow runs, cost, permissions, and prompt injection.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 6Nov 20 02:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.