Lessons
1A pattern language for AI48 min read
AI UX is not one component — it is a small, reusable vocabulary: suggestion, citation/provenance, permission/control, and uncertainty. The canonical libraries (HAX, PAIR, NN/g), the named patterns inside each domain, the shipped products that got them right and wrong, and how to choose a pattern by blast radius rather than by what looks nice.
- →AI Pattern Systems
- →Control Across Surfaces
2Naming & terminology46 min read
Naming is the highest-leverage, lowest-cost AI pattern work — and the foundation an AI design system has to fix first. How Microsoft, Google, and Adobe standardised their AI vocabularies, the three-layer naming taxonomy (capability · model family · trust tier), why names are now read by agents as well as humans, and the failure modes of ad-hoc naming.
- →AI Pattern Systems
- →AI Naming and Voice
3Provenance: authored vs suggested vs executed49 min read
Provenance is a three-mode model, not a binary “AI-generated” badge. Authored / suggested / executed each generate different design primitives, the user decision and rollback cost differ for each, and the sparkle icon is becoming a cross-product standard whose semantics are not yet locked. Adobe Content Credentials, IBM Carbon’s AI Label, Cloudscape, ServiceNow Horizon — the shipped systems and what to steal.
- →Provenance and Trust
- →Control Across Surfaces
4Consistency across unpredictable output47 min read
You cannot promise the same paragraph twice — but you can promise the same uncertainty surface. The five hallucination-mitigation patterns NN/g names, the bounded-container approach to variable-length output, confidence at the point of prediction, why warnings must activate at the low-confidence moment instead of sitting at page-bottom, and how a token-and-component system keeps a design coherent when the model does not.
- →Consistent Uncertainty
- →AI Pattern Systems
5Capstone: an AI-suggestion pattern across 3 surfaces50 min read
The canonical AI-design exercise: design one reusable AI-suggestion pattern and apply it consistently across three surfaces. The staged 8-step framework reviewers grade on, the pattern spec (states, confidence, provenance, controls), how to make it survive three surfaces without re-inventing, the metrics to name, and a rehearsal of the portfolio-walkthrough probes — pulling every pattern from the track together.
- →AI Pattern Systems
- →Control Across Surfaces
- →Consistent Uncertainty
Skills in this course
- 01AI Pattern SystemsSpecify reusable AI patterns by intent, state, risk, and surface.
- 02Control Across SurfacesMatch permissions, confirmation, and recovery to action consequence.
- 03Provenance and TrustDistinguish authored, suggested, and executed work with inspectable history.
- 04Consistent UncertaintyKeep variable output, confidence, and failure states coherent across products.
- 05AI Naming and VoiceUse a stable terminology system for capabilities, states, and trust levels.