Patterns
Progressive Disclosure
The AI design pattern library. One citation-backed pattern, read in 90 seconds.
A pattern is one researched, cited guideline for designing AI, read in 90 seconds.
Category
Track
- 09Track A
Don't dress the AI up as a person
Honest representation
anthropomorphismtransparencytrust - 08Track A
Layer AI explanations: short in the flow, deep on request
Explainability
explainabilitytransparencycitations - 07Track A
Help users specify intent without prompt gymnastics
Intent specification
intent specificationprompt controlsarticulation barrier - 06Track A
Show the plan before the agent runs it
Agent oversight
agentsoversightprogress feedback - 05Track A
Ask a clarifying question instead of guessing, but only when it matters
Mixed initiative
mixed initiativeclarifying questionsuncertainty - 04Track A
Treat AI errors as the default case, not the edge case
Graceful failure
graceful failureerror handlingrecovery - 03Track A
Set capability expectations before the first prompt
Expectation setting
expectation settingonboardingcalibrated trust - 02Track A
Design for honest pushback, not agreement
Calibrated trust
calibrated trustsycophancypushback - 01Track A
Audit AI features against the classic heuristics and the AI guidelines
Usability heuristics
foundationsheuristicsexpectation setting