Pattern Category
Trustworthy & Reliable AI
Trustworthy AI patterns are the UX primitives for building AI that communicates its limits honestly. These patterns cover how to show confidence, explain decisions, recover from errors, and build calibrated trust — the difference between users who rely on AI and users who override it on every task.
9 patterns in this category
Explainable AI (XAI)
Make AI decisions understandable via visualizations, explanations, and transparent reasoning.
Responsible AI Design
Prioritize fairness, transparency, and accountability throughout AI lifecycle.
Error Recovery & Graceful Degradation
Fail gracefully with clear recovery paths when things go wrong.
Safe Exploration
Provide sandbox environments for experimenting with AI without risk.
Confidence Visualization
Display AI certainty levels through visual indicators, helping users understand prediction reliability and decide when to trust or verify outputs.
Plan Summary
Provide a structured breakdown of the agent's reasoning and approach - showing goal interpretation, strategy, subtask checklist, and assumptions - so users can evaluate the plan before execution begins.
Action Audit Trail
Provide a timestamped, structured log of every action the agent took - grouped by task, with reversibility status, selective undo, and diff views - so users can review and correct agent behavior after the fact.
Trust Calibration
Design a system that progressively builds appropriate trust through demonstrated competence - showing track records per domain, celebrating milestones, and adjusting oversight based on actual agent performance.
Agent Reflection & Learning
Show users what the agent has learned from corrections so trust builds through visible, cumulative improvement.