Pattern #10 · Calibrated trust

Design for appropriate reliance, not maximum trust

Maximum trust is just overreliance with better branding.

Track Acalibrated-trustoverreliancetrust-in-automation

Do

Match friction to stakes: show uncertainty, link the sources to check, and in costly calls ask for the user's read before revealing the AI's.

Don't

Run user trust as a north star metric. If trust climbs while accuracy does not, you shipped persuasion, not assistance.

The rule. Aim user trust at the system's actual competence: the design target is reliance calibrated to what the AI does well and badly, not the highest trust you can induce.

Why. The foundational review of trust in automation names the goal in its title, appropriate reliance: people should neither over-depend on imperfect systems nor dismiss capable ones, and design should help users match their confidence to actual system performance (Lee & See, 2004). Both failure directions were catalogued decades before chat interfaces: misuse, relying on automation more than its reliability warrants, and disuse, neglecting capable automation, often after false alarms (Parasuraman & Riley, 1997). In AI-assisted decision-making the calibration problem survives explanation: people "accept an AI's suggestion even when that suggestion is wrong," while cognitive forcing functions such as having people decide before seeing the AI's recommendation "significantly reduced overreliance compared to the simple explainable AI approaches" (Buçinca et al., 2021).

Seen in the wild. GitHub's Copilot documentation tells developers the product "is still a tool capable of making mistakes" and that they "should always validate the code it suggests": a vendor designing its own users away from maximum trust (GitHub, n.d.).

References

  1. 01

    Lee, J. D., & See, K. A. (2004). Trust in automation: Designing for appropriate reliance. Human Factors, 46(1), 50-80. https://doi.org/10.1518/hfes.46.1.50_30392

    https://doi.org/10.1518/hfes.46.1.50_30392
  2. 02

    Parasuraman, R., & Riley, V. (1997). Humans and automation: Use, misuse, disuse, abuse. Human Factors, 39(2), 230-253. https://doi.org/10.1518/001872097778543886

    https://doi.org/10.1518/001872097778543886
  3. 03

    Buçinca, Z., Malaya, M. B., & Gajos, K. Z. (2021). To trust or to think: Cognitive forcing functions can reduce overreliance on AI in AI-assisted decision-making. Proceedings of the ACM on Human-Computer Interaction, 5, 1-21. https://doi.org/10.1145/3449287

    https://doi.org/10.1145/3449287
  4. 04

    GitHub. (n.d.). Best practices for using GitHub Copilot. GitHub Docs. Retrieved August 2, 2026, from https://docs.github.com/en/copilot/using-github-copilot/best-practices-for-using-github-copilot

    https://docs.github.com/en/copilot/using-github-copilot/best-practices-for-using-github-copilot