| UI or UX | UI + UX - Unsourced AI answer anti-pattern | UI + UX - Whole-answer source coverage and grounding evidence display | UI + UX - Inline claim-to-source evidence display for generated or summarized content | UI + UX - Calibrated reliability and uncertainty display for AI or automated predictions before user action | UI + UX - Incremental generated-output surface that renders response chunks before final completion | UI + UX - AI output correction feedback flow with selected claim, reason, scope, consent, receipt, and review state |
| UI guidance | Do not present evidence-dependent AI answers as final when no citations, grounding, source scope, or no-source status is visible. | 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 citation markers beside the claims they support, and connect each marker to a selected source preview with title, source type, excerpt, date or version, permission state, and open source action. | Render confidence and uncertainty as labelled reliability information with confidence band, reason, input scope, calibration status, review threshold, freshness, and the next safe action. | Render streamed output with a visible generation state, partial-answer label, stop control, final-complete state, and clear distinction between text that is still arriving and content that has passed final citation, safety, tool, or format checks. | Render correction feedback as an AI-output control that anchors feedback to a specific answer, claim, source, recommendation, tool result, or message instead of a detached thumbs signal. |
| UX guidance | Help users know whether they can rely on an AI answer by exposing its evidence state before they act. | Use source grounding display when users need to judge whether an AI answer is backed by the right body of evidence, not merely open one citation. | Use citation display when users must verify where a generated claim, summary, or recommendation came from without leaving the answer context. | 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. | Use a streaming response when showing partial generated output helps users start reading or monitoring work before the model finishes, and when the product can explain that early chunks may still change, be filtered, or lack final sources. | Use correction feedback when users need to tell the product that an AI answer is wrong, missing evidence, harmful, outdated, wrongly sourced, irrelevant, or should not be repeated. |
| Good UI | A support answer says Not sourced: source search was not run, offers Search help center and Ask human, and keeps Send to customer disabled until a source or override is chosen. | 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. | A policy assistant places numbered citation chips after each sourced claim; selecting a chip opens a source preview with the document title, section, quoted excerpt, updated date, and Open source action. | 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. | A policy assistant shows Answer generating, streams paragraphs into a stable answer region, marks citations pending, exposes Stop generation, then changes to Complete when citations and safety checks finish. | An assistant answer lets a user select a suspect claim, choose Wrong answer, add the expected answer and corrected source, opt out of training use, and see Feedback received with review routing. |
| Bad UI | A confident policy answer has no citations, no source scope, and no explanation that retrieval was skipped. | The answer shows a green Grounded badge even though only one citation supports one paragraph. | An answer ends with five links under Sources but no marker shows which link supports which claim. | A generated answer shows 97 percent sure without calibration, threshold, source coverage, or review path. | A generated answer appears word by word with no partial label, no stop control, and a Copy button that looks ready before sources arrive. | A thumbs-down icon accepts feedback with no selected answer, reason, expected correction, privacy choice, receipt, or indication of whether anything will change. |
| Good UX | A user sees that a customer-facing answer is unsourced, runs source search, reviews one unsupported claim, then sends only after the source state changes. | A reviewer opens the grounding panel, sees that the answer used the current policy but not the outdated FAQ, and flags one unsupported claim before publishing. | A user checks a claim, opens its source preview, compares the quoted excerpt with the answer text, and copies the citation with the source title included. | 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 the first-token state quickly, reads early outline bullets while the answer continues, stops generation after enough detail, and sees the result labelled Partial with Continue and Regenerate options. | A user flags a wrong eligibility answer, attaches the correct policy source, applies the correction to the current answer only, and receives a reviewer-routed status. |
| Bad UX | A user sends an unsourced renewal-policy answer to a customer because the fluent answer looked complete. | A user trusts a generated answer because the product says Grounded, but the source scope was only web search and did not include internal policy. | A user trusts a generated compliance claim because it has a number beside it, but the number points to an unrelated source. | Users treat a high-confidence label as proof even though the answer has no source grounding and the claim still needs evidence. | A user copies an early legal recommendation before the final paragraph reverses the conclusion after a tool result arrives. | A user reports that a cited source is wrong, but the feedback is stored as an undifferentiated dislike and future answers keep using the same bad source. |
| Best fit | A generated answer makes source-dependent claims but no source route is visible. | Users need answer-wide evidence coverage before trusting generated content. | Users need to verify generated claims, summaries, recommendations, or extracted facts against source material. | Users must judge whether an AI prediction, classification, recommendation, extraction, risk score, or generated answer is reliable enough to use. | Generated text or structured content can be read or monitored before completion. | Users can identify wrong, unsupported, stale, unsafe, biased, irrelevant, or wrongly sourced AI output after it is generated. |
| Avoid when | The answer is explicitly creative, brainstorming, stylistic, or personal drafting and does not claim factual support. | The system cannot determine source scope, retrieval status, or claim support reliably. | The product cannot reliably map claims to sources or label unresolved citations honestly. | The system cannot estimate uncertainty or calibration honestly. | Intermediate chunks may expose unsafe, private, or misleading content. | The only need is a lightweight satisfaction signal that will not be used to correct AI behavior or output. |
| Required state | Sourced answer state with citations or grounding visible. | Default grounded state with source scope, searched sources, retrieved sources, used sources, and supported-claim count. | Default answer with cited claims and inline citation markers. | High confidence state with calibration scope, reason, and whether direct apply is allowed. | Queued or receiving state before first output arrives. | Initial AI answer state with feedback entry points attached to the answer, individual claims, citations, recommendations, or tool-derived values. |
| Accessibility burden | Expose source state as text near the answer and in status regions, not only as color or icon. | Expose grounding summary, source scope, status counts, unsupported claims, and source groups as text. | Give citation markers accessible names that include their selected state and source status, such as Citation 2, verified source, or Citation pending. | Expose confidence label, uncertainty reason, threshold, freshness, and gated action as text rather than relying on color, position, or animation alone. | Expose stream milestones such as started, still generating, stopped, failed, citation ready, and complete as status messages. | Expose selected claim, selected source, reason, scope, privacy choice, submission state, receipt, review state, and outcome as text. |
| Common misuse | Showing a polished answer with no citations or grounding after the user asked for a policy-backed answer. | Showing a global Grounded badge when only some claims have evidence. | Displaying a link dump below the answer instead of mapping sources to specific claims. | Showing a fake percent or exact decimal for an uncalibrated model score. | Showing a blinking cursor with no state, stop control, or elapsed feedback. | Using a thumbs-down or smiley reaction as the only mechanism for correcting wrong AI output. |