Flag AI confidence shown as fake precision when raw or uncalibrated model scores are presented as exact user-facing confidence. Use the related patterns for honest uncertainty display, bounded scalar gauges, source evidence coverage, severe consequence warnings, or approval checkpoints.
Flag AI confidence shown as fake precision when raw or uncalibrated model scores are presented as exact user-facing confidence. Use the related patterns for honest uncertainty display, bounded scalar gauges, source evidence coverage, severe consequence warnings, or approval checkpoints.
Practice the judgment: Imagine this situation: A retrieval similarity score is shown as probability that the answer is correct. Write the person's goal, choose one of these patterns, and show the state that helps the person continue. Use the decision rules and source trail below to explain your choice.
Review the underlying principle →| Dimension | AI confidence shown as fake precision | Confidence / uncertainty display | Meter | Source grounding display | Warning text | Human approval gate |
|---|---|---|---|---|---|---|
| UI or UX | UI + UX - Anti-pattern for uncalibrated or over-exact AI confidence displays | UI + UX - Calibrated reliability and uncertainty display for AI or automated predictions before user action | UI + UX - Read-only scalar value gauge within a known range | UI + UX - Whole-answer source coverage and grounding evidence display | UI + UX - Severe-consequence warning copy before an action | UI + UX - Runtime checkpoint that pauses AI or automation until an eligible human authorizes the next step |
| UI guidance | When calibration is unavailable, show a qualitative reliability state, uncertainty reason, missing input, stale model, out-of-distribution, or review-required label instead of a probability-looking number. | Render confidence and uncertainty as labelled reliability information with confidence band, reason, input scope, calibration status, review threshold, freshness, and the next safe action. | Use native meter semantics or equivalent read-only meter attributes, and pair color bands with text such as Healthy, Warning, Critical, Low, Normal, High, or Over limit. | Render source grounding as an answer-wide evidence panel that separates source scope, searched sources, retrieved sources, used sources, supported claims, partially supported claims, unsupported claims, and unresolved source states. | Render warning text as a short high-emphasis statement with a warning icon, visible or hidden warning label, and explicit consequence copy placed before the relevant action, declaration, or instruction. | Render a human approval gate as a paused automation checkpoint with the proposed action, tool or workflow step, triggering rule, risk level, payload snapshot, requester or agent, approver eligibility, timeout, and explicit approve, reject, edit, cancel, or bypass controls. |
| UX guidance | Protect users from automation bias by making confidence limits actionable: explain what the number means, where it is valid, what threshold changes the workflow, and what safe action follows. | Use confidence / uncertainty display when users need to decide whether an AI prediction, classification, recommendation, extraction, risk assessment, or generated answer is reliable enough to apply. | Explain whether higher, lower, or middle values are better, what threshold the current value crosses, and what action is available when the meter enters a warning or critical range. | Let users inspect coverage gaps, source scope, retrieval status, and unsupported claims before they copy, publish, apply, or rely on the answer. | Use warning text when users must understand a serious consequence before acting or failing to act, such as a fine, loss of access, permanent deletion, eligibility impact, or legal responsibility. | Use human approval gate when automation is ready to act but policy, risk, confidence, cost, access, publication, deployment, customer impact, or legal consequence requires a human decision before execution continues. |
| Good UI | A claim classifier says Calibration unavailable, explains that the model is outside its monitored scope, hides the 0.873 raw score, and routes to reviewer triage. | A claim classifier says Medium confidence, 71 to 78 percent calibrated range, review threshold 80 percent, conflicting account-age signal, and routes the case to manual review. | An account storage card says 86 GB of 100 GB used, marks 70 GB as warning and 90 GB as critical, and labels the current state Critical. | A policy answer includes a Grounding panel showing 4 sources searched, 3 retrieved, 2 used, 5 supported claims, 1 partially supported claim, and 1 unsupported claim with a Review action. | Before Submit declaration, a warning with an exclamation icon says the user may be fined if they provide false information. | An AI support agent pauses before issuing a refund, shows the proposed amount, customer, policy match, confidence, source grounding, approver role, timeout, Approve refund, Edit amount, Reject, and Stop run controls. |
| Bad UI | A stale confidence score remains on a regenerated answer after the source, model, and threshold changed. | Users over-trust an AI answer because a confidence badge looks authoritative. | A progress bar for uploading evidence.zip is implemented as a meter, so task completion and capacity status are confused. | The answer shows a green Grounded badge even though only one citation supports one paragraph. | A red sentence says Important below the submit button after the user has already acted. | A reviewer can approve an automation run after the action already executed, making the gate only decorative audit text. |
| Good UX | A reviewer sees that exact confidence is unavailable, opens the uncertainty reason, requests missing evidence, and avoids auto-denying a claim. | A reviewer sees low confidence and out-of-distribution input, opens the reason panel, collects the missing invoice, and avoids auto-denying the claim. | A user sees storage at 86 of 100 GB, understands the account is in the critical band, opens Manage storage, and deletes old exports before uploads are blocked. | The person reaches the intended result with clear feedback. | Users see the fine or eligibility consequence before checking the declaration and can pause to verify their answer. | A billing lead opens the paused refund gate, sees that the amount is under policy but source grounding is partial, edits the refund to the verified amount, approves, and the agent resumes only that step. |
| Bad UX | Users trust a confident-looking 98.7 percent label and send an unsupported answer to a customer. | A model update invalidates old confidence scores but the UI keeps showing them as current. | Users mistake quota level for upload completion because the meter animates like progress. | Grounded status is shown before retrieval finishes. | Users incur a penalty because the warning looked like ordinary hint text. | A human approves a stale agent action from email and the agent applies it to a different customer state. |
| Best fit | Users may make decisions, send output, approve automation, or trust generated content based on the exact-looking value. | Users must judge whether an AI prediction, classification, recommendation, extraction, risk score, or generated answer is reliable enough to use. | A current value exists inside a meaningful known range. | Users need answer-wide evidence coverage before trusting generated content. | A user must understand a serious consequence before taking or skipping an action. | An AI agent, workflow, deployment, or automation is ready to perform a high-impact step and must pause for human authorization. |
| Avoid when | The value is a validated, calibrated confidence range shown with scope, threshold, reason, and review behavior; use confidence / uncertainty display instead. | Users only need source coverage or claim evidence, which belongs to source grounding display or citation display. | The value represents task completion or loading progress. | The only task is opening one claim's source preview, which belongs to citation display. | The message is a dynamic task status that must be announced when it appears. | The action has already happened and users only need an audit log. |
| Required state | Raw score hidden state where an internal score is withheld from the user-facing decision. | High confidence state with calibration scope, reason, and whether direct apply is allowed. | Normal state inside the acceptable band. | Default grounded state with source scope, searched sources, retrieved sources, used sources, and supported-claim count. | Before-action warning state placed immediately before the related control or declaration. | Paused gate state with proposed action, payload snapshot, reason for gate, and run context. |
| Accessibility burden | Expose calibration unavailable, stale, out-of-distribution, insufficient evidence, and review-required states as text near the score. | Expose confidence label, uncertainty reason, threshold, freshness, and gated action as text rather than relying on color, position, or animation alone. | Prefer the native meter element where possible because it carries the correct read-only meter semantics. | Expose grounding summary, source scope, status counts, unsupported claims, and source groups as text. | Keep the warning in reading order before the control, declaration, or instruction it qualifies. | Expose gate status, proposed action, target, payload summary, risk, approver rule, timeout, and current run state as text. |
| Common misuse | Formatting an uncalibrated model score as 97.42 percent sure. | Showing a fake percent or exact decimal for an uncalibrated model score. | Using a meter to show task progress such as upload completion. | Showing a global Grounded badge when only some claims have evidence. | Using warning text for routine hints, explanations, or mild reminders. | Using a post-action audit record as if it were a pre-action human gate. |