Back to compare picker

Source grounding display vs Citation display vs Chat interface vs Streaming response vs Related links

Choose source grounding display when users need whole-answer evidence coverage across source scope, retrieved material, used evidence, and unsupported claims, not just one citation marker.

Decision dimensions

Dimension Source grounding displayCitation displayChat interfaceStreaming responseRelated links
UI or UX UI + UX - Whole-answer source coverage and grounding evidence displayUI + UX - Inline claim-to-source evidence display for generated or summarized contentUI + UX - Multi-turn conversation surface with transcript, composer, assistant responses, and conversation historyUI + UX - Incremental generated-output surface that renders response chunks before final completionUI + 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.

Source grounding display

UI or UX
UI + UX - Whole-answer source coverage and grounding evidence display
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.
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.
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.
Bad UI
The answer shows a green Grounded badge even though only one citation supports one paragraph.
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.
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.
Best fit
Users need answer-wide evidence coverage before trusting generated content.
Avoid when
The system cannot determine source scope, retrieval status, or claim support reliably.
Required state
Default grounded state with source scope, searched sources, retrieved sources, used sources, and supported-claim count.
Accessibility burden
Expose grounding summary, source scope, status counts, unsupported claims, and source groups as text.
Common misuse
Showing a global Grounded badge when only some claims have evidence.

Citation display

UI or UX
UI + UX - Inline claim-to-source evidence display for generated or summarized content
UI guidance
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.
UX guidance
Use citation display when users must verify where a generated claim, summary, or recommendation came from without leaving the answer context.
Good UI
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.
Bad UI
An answer ends with five links under Sources but no marker shows which link supports which claim.
Good UX
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.
Bad UX
A user trusts a generated compliance claim because it has a number beside it, but the number points to an unrelated source.
Best fit
Users need to verify generated claims, summaries, recommendations, or extracted facts against source material.
Avoid when
The product cannot reliably map claims to sources or label unresolved citations honestly.
Required state
Default answer with cited claims and inline citation markers.
Accessibility burden
Give citation markers accessible names that include their selected state and source status, such as Citation 2, verified source, or Citation pending.
Common misuse
Displaying a link dump below the answer instead of mapping sources to specific claims.

Chat interface

UI or UX
UI + UX - Multi-turn conversation surface with transcript, composer, assistant responses, and conversation history
UI guidance
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.
UX guidance
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.
Good UI
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.
Bad UI
A chat panel shows one undifferentiated wall of text with no user or assistant roles, no submitted prompt, and no visible conversation identity.
Good UX
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.
Bad UX
A follow-up uses prior conversation context after chat history has been switched off, without explaining that current-session context still exists.
Best fit
The user needs a back-and-forth assistant conversation with follow-up questions and answer refinement.
Avoid when
The task can be completed with a single structured prompt box, form, or command.
Required state
Empty new chat with conversation title, mode, history or retention status, and a labelled composer.
Accessibility burden
Expose the transcript as an ordered region and use a sequential update strategy such as role=log for appended messages where appropriate.
Common misuse
Treating chat as a large textarea plus latest answer with no durable turn identity.

Streaming response

UI or UX
UI + UX - Incremental generated-output surface that renders response chunks before final completion
UI guidance
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.
UX guidance
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.
Good UI
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.
Bad UI
A generated answer appears word by word with no partial label, no stop control, and a Copy button that looks ready before sources arrive.
Good UX
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.
Bad UX
A user copies an early legal recommendation before the final paragraph reverses the conclusion after a tool result arrives.
Best fit
Generated text or structured content can be read or monitored before completion.
Avoid when
Intermediate chunks may expose unsafe, private, or misleading content.
Required state
Queued or receiving state before first output arrives.
Accessibility burden
Expose stream milestones such as started, still generating, stopped, failed, citation ready, and complete as status messages.
Common misuse
Showing a blinking cursor with no state, stop control, or elapsed feedback.

Related links

UI or UX
UI + UX - Curated onward links connected to the current content
UI guidance
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 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 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
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 user reads claim renewal guidance, chooses Upload evidence for your claim, and sees why that destination is the next useful service page.
Bad UX
Users follow a generic More information link and land on an unrelated policy collection.
Best fit
The current page has a few genuinely adjacent pages, services, programs, or resources users often need next.
Avoid when
Links are only loosely associated by topic tags or organizational ownership.
Required state
Default state with a labelled, curated related-links block and descriptive link text.
Accessibility burden
Use descriptive link text that makes sense out of context.
Common misuse
Using related links as a catch-all further-reading dump.
Decision rules
  • Choose source grounding display when users need whole-answer evidence coverage across source scope, retrieved material, used evidence, and unsupported claims, not just one citation marker.
  • Choose citation display when the task is opening a selected claim-level source preview, quote, metadata, and open source action.
  • Choose chat interface when the main design problem is the conversation transcript, multi-turn container, prompt composer, history, and follow-up context.
  • Choose streaming response when the product must expose partial generated output, pending source events, stop generation, or response failure while text arrives.
  • Choose related links when destinations are optional onward navigation, not evidence used by the generated answer.
  • A source grounding display must name source scope, searched sources, retrieved sources, used sources, unsupported claims, partial support, missing sources, permission-limited sources, stale sources, and out-of-scope answer parts.
  • Show grounded, partially grounded, unsupported, source unavailable, permission-limited, stale, retrieval failed, and not searched states separately.
  • Do not collapse source grounding into a single confidence score; source coverage, source quality, permissions, recency, and claim support are different evidence dimensions.
  • When grounding is still resolving during a stream, show pending source coverage and delay answer-wide grounded status until retrieval and final answer text settle.
  • If no suitable source is found, say no supporting source found rather than displaying unrelated links or decorative citations.
Inspect live examples
Failure modes
  • The answer shows citations but hides that several claims are unsupported.
  • The display claims the whole answer is grounded when only one paragraph has a source.
  • Retrieved sources, used sources, and available source scope are mixed together so users cannot tell what evidence was actually used.
  • Permission-limited or stale sources look the same as checked sources.
  • A single confidence badge replaces source coverage, unsupported claims, and retrieval status.
  • The UI shows related links as if they were grounding evidence for the answer.