AIUX
Interface patterns for AI products
AIUX is the design of products whose output is generated rather than retrieved. These are the recurring problems that come with that and what actually resolves them: what to do when the model is wrong, which claims the interface should vouch for, when an agent should not be a chat, and how to tell whether a change helped.
Each of the 6 patterns is grounded in something shipped — a product in the case studies on this site, or a count taken from the system behind them — rather than read off someone else’s release notes. It is a working vocabulary, not a survey, so it grows when a project teaches something and not otherwise.
- 01
Interaction model
Wizard or conversation
Choose a conversation only when you can't know the request in advance; otherwise let an agent fill in a structured flow and stop at the review step.
agents · flows · chat
- 02
Failure and recovery
Design the failure state first
Draw the wrong-answer screen before the right-answer one — “the model failed” is five different situations that each need a different interface.
errors · empty states · trust
- 03
Failure and recovery
Undo over confirm
Apply the change immediately and hold the irreversible commit until the undo window closes — for an agent acting on someone's behalf, that staging point is the design.
agents · destructive · recovery
- 04
Trust and uncertainty
Mark what the product vouches for
One answer mixes quoted fact, fair summary and plausible invention — decide per claim whether the interface vouches for it, sources it, or declines to stand behind it.
trust · citations · uncertainty
- 05
Data boundaries
Redaction moves to the export
Local inference doesn't delete the privacy boundary, it moves it — from the network call to the export, where content actually leaves the user's control.
privacy · on-device · enterprise
- 06
Measurement
Evaluation loops
Keep twenty real cases fixed, run them after every change, and grade what the screen does — a single try tells you nothing when the output moves.
evals · measurement · process
Using these
Every pattern links to the long-form argument behind it in the writing archive. If you are deciding one of these for a product right now, that is most of what a fractional engagement is: making the call and writing down why, so it settles an argument when nobody is in the room.