Trust Calibration
What is Trust Calibration?
Users either over-trust or under-trust AI agents. Over-trust leads to passive reliance on inaccurate outputs where users stop checking and mistakes compound. Under-trust means users micromanage every action, defeating the purpose of delegation. Trust calibration is the design challenge of aligning a user's perception of the agent's reliability with its actual performance over time. Unlike one-time confidence scores, this is a relationship that evolves - the agent earns more or less trust based on its track record with that specific user. The pattern starts agents supervised with high visibility, shows per-domain track records, proactively repairs trust after mistakes, and offers autonomy upgrades only when earned. Trust builds slowly and breaks quickly, and the design must account for this asymmetry.
Example: GitHub Copilot - Acceptance-Calibrated Suggestions
Initial Copilot suggestions stay conservative and well-established. As the developer accepts more inline completions, suggestions grow longer and more opinionated — calibrated to a working trust level inferred from acceptance rate. Rejecting suggestions for similar contexts pulls confidence back down.
AI Design Prompt
Want to learn more about this pattern?
Explore the full pattern with real-world examples, implementation guidelines, and code samples.
View Full Pattern