ux-research 3 linked patterns checked
People + AI Guidebook
Practical guidance for human-centered AI products, including user trust, expectations, explanation, feedback, and uncertainty-aware AI product decisions.
Read with a purpose
What this source can teach
Use this source to examine the study question, participants, observations, and limits before applying a finding.
- Start with the original. Open the source and find the guidance or example relevant to your task.
- Trace the connection. Use the claim notes below to see how this site applies the source to specific patterns.
- Check the setting. Compare the source's platform, people, and constraints with your own decision.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| Confidence / uncertainty display | Choose confidence / uncertainty display when users need to judge prediction reliability before acting on AI or automation output. | The display names the task, prediction, source of the confidence estimate, calibration scope, and last calibration or update time when available. | Supports human-centered AI design guidance around expectations, explanation, feedback, and trust. |
| Correction feedback | Choose correction feedback when users need to correct AI output, source use, assumptions, recommendations, safety behavior, or answer quality after an AI response is shown. | A correction feedback action preserves answer ID, response version, claim span, source ID, user reason, expected correction, submitter, timestamp, and chosen scope. | Supports human-centered AI feedback, expectations, explanation, and trust decisions. |
| Scope clarification | Choose scope clarification when the AI needs a missing boundary before producing a reliable answer, plan, retrieval query, or tool action. | The system identifies what boundary is missing before asking the user to clarify. | Supports expectation setting, trust, explanation, and uncertainty-aware AI decisions. |
Comparisons supported by this source
- Confidence / uncertainty display vs source grounding display vs citation display vs meter vs warning text
Supports human-centered AI product guidance for expectations, explanations, feedback, and user trust.
- Correction feedback vs query correction vs inline validation vs comments vs regenerate / retry vs editable AI output
Supports human-centered AI feedback, expectations, explanation, and trust decisions.
- Scope clarification vs prompt box vs search scope selector vs agent plan preview vs human approval gate vs chat interface
Supports expectation setting, trust, explanation, and uncertainty-aware AI decisions.
Evidence Role
This source is treated as ux-research evidence. Its value comes from the specific claims and setting described above.
Publisher: Google PAIR. Last checked: .