Field guide
Guide 07 / 10Pattern field guide3 min

Chat Was Never the Interface: A Field Guide to Emerging AI Design Patterns

Seven interaction patterns worth stealing (receipts, ghost text, preview-then-commit, earned autonomy) and the anti-patterns to name and kill.

Chat earned its moment. It's the fastest way to demo a model and the cheapest way to ship one. But a chat box quietly hands the user three jobs the interface should be doing: figure out what to ask, figure out how to ask it, and figure out whether to believe what comes back.

The AI products people actually keep don't make users do all three. They use a small set of interaction patterns that do the work on-screen. None of them are exotic. All of them are stealable.

Seven patterns worth stealing

PatternWhat it doesYou've seen it in
Receipts on everythingSources, reasoning, and an honest confidence signal attached to output — believing doesn't require faithPerplexity's citations
Ghost textThe AI suggests inline, dismissible with one keystroke; the user stays the authorGitHub Copilot
Preview, then commitShow what will change before it changes; keep one-step undo afterPhotoshop's Generative Fill on a new layer
Visible workStreaming and progress that names what's happening ("reading your March invoices…") instead of a silent spinnerEvery agent product worth trusting
Co-creation loopsTreat the first output as a draft to refine together, not a verdict — most users edit the AI's first attempt anywayAI writing tools people actually reuse
The ledgerBackground work leaves a trail: what the agent did, why, and how to reverse itActivity feeds and audit trails in agent tools
Earned autonomyStart with suggestions the user approves; let the AI do more alone as wins accumulate"Review and approve" flows that graduate to automation

Notice what they share: every one makes the AI's work easier to judge. That's not a coincidence — judging the work is the user's real job now. (The Gulfs Have Flipped makes the full argument.)

The anti-patterns — naming them helps

  • Mystery AI. Features that pop up unpredictably, look different on every screen, and can't be invoked on purpose. Users can't build a habit around a ghost.
  • Confidence theater. A confidence badge that changes nothing. If "low confidence" doesn't change what the interface asks of the user, it's decoration.
  • Sparkle-washing. An ✨ on every feature, value on none. Users learned this tell fast, and it now reads as a warning label.
  • The 3,000-word answer. Dumping everything the model knows on someone who asked a small question. You don't look smart; you look noisy.

Try this — the pattern audit

List every AI surface in your product. Next to each, write the pattern it uses. Two findings are common, and both are fixable:

  • If every line says "chat," you shipped a demo. Take the highest-traffic surface and rebuild it around receipts, previews, or ghost text.
  • If the patterns differ screen to screen — approval here, silent overwrite there — users have to relearn trust in every corner of your product. Turn the patterns into shared components with one behavior. (Trust Is Not a Feeling covers how.)
Go deeper: why patterns beat one-off cleverness

Patterns turn trust into a component problem, and component problems scale. When confidence, preview, and undo are reusable pieces with consistent rules, every new feature inherits trustworthy behavior instead of reinventing it — and the coding agents helping you build can be instructed once, in writing, instead of corrected feature by feature. One-off clever interactions demo well and drift immediately.

Chat will keep its place — for the jobs where conversation is the point. For everything else, the interface is finally growing up.

Next guide

08The Bottleneck Moved: How Iteration Changed When Building Became Free

Iteration when building is nearly free: the five-day loop, the kill rate, and why shipped slop spends user trust.