| UI or UX | 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 - Multi-turn conversation surface with transcript, composer, assistant responses, and conversation history | UI + UX - Incremental generated-output surface that renders response chunks before final completion | UI + UX - Curated onward links connected to the current content |
| UI guidance | 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 chat as an ordered transcript with visible user and assistant roles, turn boundaries, timestamps or relative position, current draft composer, submitted prompt, response status, source or tool indicators, and conversation-level controls. | 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 a short, labelled collection of links whose destinations are closely related to the current content, using destination-specific link text and optional relation labels such as service, guidance, external, or PDF. |
| UX guidance | 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 a chat interface when users need a multi-turn assistant conversation where later prompts can depend on earlier turns, responses can be inspected or continued, and conversation history can be saved, resumed, deleted, or limited by policy. | 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 related links to support users who have finished or understood the current content and need a relevant next page, adjacent service, reference, or follow-up resource. |
| Good UI | 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 research assistant chat shows user and assistant bubbles, turn numbers, source chips, streaming status, Stop, Copy answer, Regenerate, New chat, and a conversations list with the active chat title. | 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. | A benefits guidance page ends with Related links: Check eligibility for support, Upload evidence for your claim, and Appeal a support decision, each with a concise relation label. |
| Bad UI | 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 chat panel shows one undifferentiated wall of text with no user or assistant roles, no submitted prompt, and no visible conversation identity. | 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 page ends with More information containing Home, Contact us, Apply now, Old 2018 guidance, Help, and an unrelated account settings link. |
| Good UX | 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 user asks for a policy summary, follows up with Compare that to the renewal clause, sees that the second answer used the first answer and selected file, then exports the two-turn transcript. | 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 reads claim renewal guidance, chooses Upload evidence for your claim, and sees why that destination is the next useful service page. |
| Bad UX | 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. | A follow-up uses prior conversation context after chat history has been switched off, without explaining that current-session context still exists. | A user copies an early legal recommendation before the final paragraph reverses the conclusion after a tool result arrives. | Users follow a generic More information link and land on an unrelated policy collection. |
| Best fit | Users need answer-wide evidence coverage before trusting generated content. | Users need to verify generated claims, summaries, recommendations, or extracted facts against source material. | The user needs a back-and-forth assistant conversation with follow-up questions and answer refinement. | Generated text or structured content can be read or monitored before completion. | The current page has a few genuinely adjacent pages, services, programs, or resources users often need next. |
| Avoid when | 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 task can be completed with a single structured prompt box, form, or command. | Intermediate chunks may expose unsafe, private, or misleading content. | Links are only loosely associated by topic tags or organizational ownership. |
| Required state | 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. | Empty new chat with conversation title, mode, history or retention status, and a labelled composer. | Queued or receiving state before first output arrives. | Default state with a labelled, curated related-links block and descriptive link text. |
| Accessibility burden | 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 the transcript as an ordered region and use a sequential update strategy such as role=log for appended messages where appropriate. | Expose stream milestones such as started, still generating, stopped, failed, citation ready, and complete as status messages. | Use descriptive link text that makes sense out of context. |
| Common misuse | 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. | Treating chat as a large textarea plus latest answer with no durable turn identity. | Showing a blinking cursor with no state, stop control, or elapsed feedback. | Using related links as a catch-all further-reading dump. |