Agent UX
Comes up in: AI system design, Frontend system design
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- transparency (plans, steps, sources)
- control (pause, stop, edit, undo)
- progress for long tasks
- trust calibration
- error recovery
- notifications for async agents
Words you will know
What you will practise
- UX spec for a background research agent
Interview questions this answers
- How do you design the UX of an agent that runs for 20 minutes?