AI Design

Product and UX patterns for shipping AI features.


AI features fail in user-facing ways that traditional features don't. The model is stochastic, slow, and sometimes wrong. Good design absorbs that.

Principles

  • Show the work. Cite sources, surface tool calls, render intermediate steps. Trust comes from visible reasoning, not confident output.
  • Make undo cheap. Anything destructive needs a confirmation step or a reversible action. Autopilot only where the cost of being wrong is low.
  • Give the user something to do while it thinks. Stream tokens, show a skeleton, narrate the plan. Empty loading states feel twice as long.
  • Default to drafts, not commits. Generate into a state the user has to accept. Pre-filled forms, not auto-submitted ones.
  • Fail explicitly. When the model can't answer, say so. Hallucinated confidence is worse than a missing answer.

Patterns worth stealing

PatternWhere it works
Inline citationsPerplexity, Notion AI: every claim links back
Suggestion chipsChatGPT, Cursor: show possible next prompts
Diff view for editsCursor, Linear AI: never overwrite silently
"Working..." narrationClaude, Devin: say what the agent is doing right now
Cancel buttonEvery good chat UI: long runs need an escape hatch

Anti-patterns

  • A spinner with no text. Users assume it's broken after 3 seconds.
  • "I'm an AI and I can't do that." Either do it or fail with a real error.
  • Long answers when one sentence would do. Match length to the question.
  • Asking the user to write a prompt from scratch. Most users don't know what to type. Suggest something.

Reading