Interaction study
Ten drives, two ways to say yes.
The bulk review pattern from my MileIQ work, with the counters running. The same ten suggested classifications run under two confirmation models, and the only variable is what the default does. Run both and the counters keep score.
Pick a model · tap chips to confirm or flip · marks the model’s suggestion · the footer is live
PER personal · BIZ business · suggested10 DRIVES
The default does most of the work. Flipping exceptions inherits the model’s accuracy as its error floor, so it’s only faster when exceptions are cheap to spot, which is why the shipped feature paired bulk accept with a visible recommendation mark and one-tap undo.
SERIES · PROTO_02: Set the line → · PROTO_03: One field → · PROTO_04: Swipe to classify →