The library
11 patterns, shown in the products that shipped them.
Each entry is named, categorized, and illustrated with real examples — plus the analysis screenshots can't give you: why it works, what to steal, what to skip. Where a canonical name exists, we cite it.
Invoke
Getting started and steering: how products turn a blank box into a beginning.
Observe
Watching AI work: reasoning, progress, live workspaces, and system honesty under load.
Live Viewport
named hereA window into the agent's workspace — watch it browse, click, and build in real time.
Scarcity States
named hereHonest UX for the moment the AI runs out — of capacity, quota, or compute.
Stream of Thought
Show the model's reasoning as it happens, so waiting becomes watching.
Verify
Trust and grounding: how claims get sourced, checked, and made inspectable.
Control
Agent oversight: plans, permissions, interruption, and the cost of autonomy.
Action Plan
The agent proposes its plan and waits for approval before touching anything.
Barge-in
named hereInterrupt the AI mid-stream — with voice, a tap, or an escape key — without losing the session.
Credit Metering
named hereMake the cost of generation visible — and spendable — inside the flow.
Remember
Memory and personalization: what the AI keeps, and who's in charge of it.
Transact
AI meets commerce and services: when the conversation becomes the storefront.
Newsletter
New patterns and product teardowns from across the AI landscape — what to steal, what to skip, from someone who actually uses them.