Interaction Design for AI
Latency and streaming affordances, error recovery, steering controls, and designing for probabilistic output.
5concepts
58flashcards
35minutes of reading
- 01 Designing for Probabilistic Output Why interfaces built on the assumption of correct output fail when output is usually correct, the design moves that make errors survivable, and the cost of hiding uncertainty.
- 02 Latency, Streaming and Perceived Speed Why time to first token dominates perceived speed, how streaming changes what users tolerate, and the interaction costs that come with it.
- 03 Feedback Collection That Is Worth Having Why thumbs-up and thumbs-down produce almost no usable signal, which implicit behaviours carry more information, and how to collect explicit feedback that can actually train something.
- 04 Interfaces for Multi-Step Agents What changes when the system acts over minutes rather than responds in seconds, how to make a long trajectory legible without demanding constant attention, and where the intervention points belong.
- 05 Steering, Correction and Repair What a user does when the output is nearly right, why regeneration is the wrong primary affordance, and the controls that let someone converge rather than resample.