Response feedbackPro

• Type: Component (special)
• Access: Xzero Pro
• Page: https://ui.xzero.co.uk/components/response-feedback
• Markdown: https://ui.xzero.co.uk/components/response-feedback/markdown
• Source file: registry/components/response-feedback/response-feedback.tsx
• Dependencies: motion, lucide-react, @radix-ui/react-tooltip
• Keywords: special, ai, new, thumbs up, thumbs down, feedback, ai feedback, response rating, message actions, rlhf, helpful, chat feedback, reasons, llm evaluation

When to use

• Collecting thumbs up and down on AI replies in a chat, copilot or search answer.
• Gathering structured reasons (inaccurate, unsafe) for model evaluation or support triage.
• Adding a message action row with copy and regenerate next to feedback.

When not to use

• Star or numeric ratings of a product or session: use rating.
• General product feedback not tied to one reply: use feedback-morph.
• Long surveys with many questions: use a form or dialog.

Installation

Register both Xzero UI namespaces in your project's components.json:

{
  "registries": {
    "@xzero-ui": "https://mcp.xzero.co.uk/r/{name}.json",
    "@xzero-ui-pro": "https://mcp.xzero.co.uk/r/pro/{name}.json"
  }
}

npx shadcn@4.23.0 add @xzero-ui-pro/response-feedback

Install xzero-foundation once, and import @/components/xzero/foundation.css in your app root. No Xzero token is used by this snapshot. For sample portraits, photos, fonts, or logos, download https://mcp.xzero.co.uk/install-assets.mjs and run node xzero-install-assets.mjs <receiving-project>.

Usage

import { FeedbackActions, ResponseFeedback } from "@/components/xzero/response-feedback/response-feedback";

// The full reply card
<ResponseFeedback
  model={{ name: "Claude Opus 5.5" }}
  prompt={question}
  copyText={answerText}
  messageId={message.id}
  onFeedback={async (event, { signal }) => {
    await fetch("/api/feedback", { method: "POST", body: JSON.stringify(event), signal });
  }}
>
  <Markdown>{answerText}</Markdown>
</ResponseFeedback>

// Just the control, inside your own message row
<FeedbackActions
  messageId={message.id}
  defaultRating={message.rating}
  leading={<CopyButton value={answerText} iconOnly variant="plain" label="Copy reply" />}
  onFeedback={saveFeedback}
/>

API reference

ResponseFeedback

An AI reply card: optional prompt bubble, model mark and name, the reply body and an action row with copy, optional regenerate and the thumbs feedback control. With no props it renders a sample Claude Sonnet 5.5 answer with simulated feedback. Accepts every FeedbackActions prop except leading.

Prop	Type	Default	Description
model	{ name: string; mark?: ReactNode }	{ name: "Claude Sonnet 5.5" }	The model that wrote the reply. The mark is drawn at 16px and defaults to the Claude mark.
prompt	ReactNode | null	–	The person's message shown above the reply. Defaults to a sample question; pass null to hide it.
children	ReactNode	–	The reply body. Paragraphs, lists and inline code are styled. Defaults to a sample Postgres answer.
copyText	string | null	–	Plain text for the copy action. Defaults to the sample reply when no children are given; pass null to hide copy.
onRegenerate	() => void	–	Shows a regenerate action in the row.
onFeedback	(event: FeedbackEvent, context: { signal: AbortSignal }) => void | Promise<void>	–	Persists feedback. Fires with stage "rating" on every thumb press and stage "details" when reasons or a note are submitted. Reject to show the inline error and Try again; the signal aborts when the panel closes or the rating changes. Without it, sends are simulated.
messageId	string	–	Passed back on every event so feedback can be stored against a message.
rating	"up" | "down" | null	–	Controlled rating. Leave undefined to let the control own it.
defaultRating	"up" | "down" | null	null	Initial rating when uncontrolled, for example a rating loaded from your database.
onRatingChange	(rating: "up" | "down" | null) => void	–	Called on every rating change, including clearing it by pressing the active thumb again.
negativeReasons	string[]	["Inaccurate", "Not helpful", "Too long", "Unsafe", "Other"]	Reason chips offered after a thumbs down. A chip labelled Other moves focus to the note and changes its placeholder.
positiveReasons	string[]	["Accurate", "Easy to follow", "Good examples", "Saved me time"]	Chips offered after a thumbs up. Pass [] to skip the follow-up row.
allowComment	boolean	true	Shows the optional note field after a thumbs down.
commentPlaceholder	string	"Add details (optional)"	Placeholder for the note field.
commentMaxLength	number	1000	Maximum note length.
privacyNote	ReactNode	"Shares this reply for review"	Quiet line next to Submit about what gets shared. Hidden below 400px of container width.
thanksMessage	ReactNode	–	Second line of the thank-you state. Defaults to a simulated note without onFeedback, otherwise "It helps improve future replies."
thanksDuration	number	1600	How long the thank-you state holds before the panel folds away, in ms.
trailing	ReactNode	–	Content pinned to the end of the row, such as a timestamp or token count.
disabled	boolean	false	Disables the thumbs, for example while the reply is still streaming.
className	string	–	Class on the root element.

FeedbackActions

The feedback control on its own, for your own message rows: thumbs up and down, the reasons panel, the What was good row and the thank-you state.

Prop	Type	Default	Description
leading	ReactNode	–	Actions rendered before the thumbs, such as copy or regenerate. Use 16px icons in control-height-sm buttons to match.
onFeedback	(event: FeedbackEvent, context: { signal: AbortSignal }) => void | Promise<void>	–	Persists feedback. Fires with stage "rating" on every thumb press and stage "details" when reasons or a note are submitted. Reject to show the inline error and Try again; the signal aborts when the panel closes or the rating changes. Without it, sends are simulated.
messageId	string	–	Passed back on every event so feedback can be stored against a message.
rating	"up" | "down" | null	–	Controlled rating. Leave undefined to let the control own it.
defaultRating	"up" | "down" | null	null	Initial rating when uncontrolled, for example a rating loaded from your database.
onRatingChange	(rating: "up" | "down" | null) => void	–	Called on every rating change, including clearing it by pressing the active thumb again.
negativeReasons	string[]	["Inaccurate", "Not helpful", "Too long", "Unsafe", "Other"]	Reason chips offered after a thumbs down. A chip labelled Other moves focus to the note and changes its placeholder.
positiveReasons	string[]	["Accurate", "Easy to follow", "Good examples", "Saved me time"]	Chips offered after a thumbs up. Pass [] to skip the follow-up row.
allowComment	boolean	true	Shows the optional note field after a thumbs down.
commentPlaceholder	string	"Add details (optional)"	Placeholder for the note field.
commentMaxLength	number	1000	Maximum note length.
privacyNote	ReactNode	"Shares this reply for review"	Quiet line next to Submit about what gets shared. Hidden below 400px of container width.
thanksMessage	ReactNode	–	Second line of the thank-you state. Defaults to a simulated note without onFeedback, otherwise "It helps improve future replies."
thanksDuration	number	1600	How long the thank-you state holds before the panel folds away, in ms.
trailing	ReactNode	–	Content pinned to the end of the row, such as a timestamp or token count.
disabled	boolean	false	Disables the thumbs, for example while the reply is still streaming.
className	string	–	Class on the root element.

Keyboard interactions

Keys	Action
Tab	Moves through copy, thumbs up and thumbs down, then into the open panel.
Enter / Space	Presses a thumb, toggles a reason chip, or activates Submit, Send, Skip and Cancel. Pressing the active thumb clears the rating.
Escape	Closes the open panel and returns focus to the thumb that opened it. The rating stays.
Cmd / Ctrl + Enter	Submits from the note field.

Accessibility

• Thumbs are toggle buttons with aria-pressed and labels Good response and Bad response; aria-expanded and aria-controls point at the panel while it is open.
• Reason chips are toggle buttons with aria-pressed inside a labelled group. Selected chips invert to a solid fill, so the state never relies on hue.
• A keyboard press on thumbs down moves focus to the first reason; a pointer press leaves focus where it is. After a keyboard submit, focus lands on the thank-you line and returns to the thumb when the panel folds.
• A polite live region announces rating changes, sending, the thank-you state, errors, and says when nothing was sent because the send is simulated.
• Errors show an icon and text next to the actions, and Submit becomes Try again.

Motion

• The panel opens and closes on a bounce-free spring (0.24s visual duration) that animates measured height, with a 160ms opacity fade.
• Switching between the form and the thank-you line is a single crossfade (out 100ms, in 160ms, 2px rise) while the panel height springs to the new content.
• The filled thumb fades in over 160ms on top of the outline, so nothing moves or resizes. Presses scale to .94 instantly and release on a spring.
• The success tick draws once in 280ms.
• Reduced motion: height changes cut instantly, the panel only fades, and press scales are dropped. All end states and announcements stay.

Responsive behavior

• The card pads 16px below 480px of container width and 24px above; the panel and chips wrap, so it holds at 360px without horizontal scroll.
• Below 400px of container width the privacy note and Cancel give way (Close covers Cancel), so the error line and Try again always fit on one row.
• Chips grow to 32px tall on coarse pointers.

Performance

• Two small motion trees (panel height and content crossfade) mount only while the panel is open.
• One ResizeObserver per open panel animates content height changes; it disconnects when the panel closes.
• No timers run while idle; the thank-you timer and in-flight sends are cleared on unmount.

Notes for AI

• Use ResponseFeedback for a single assistant reply with its actions; use FeedbackActions when you already render your own messages.
• Persist both stages: store the rating on stage "rating" (null means cleared) and attach reasons and the note on stage "details". Always pass messageId.
• Throw or reject from onFeedback to show the error state; the component handles Try again and aborts stale calls through the signal.
• Set disabled while the reply is still streaming, so people rate the finished answer.
• Keep reason labels short (one or two words) so the chips stay on one or two lines at 360px.

Related

• Chat thread: A chat thread with grouped messages, reactions, read receipts, typing, and a composer with attachments.
• Copy button: Copy a value with immediate confirmation.
• Tool call: A tool call row for agent transcripts: the tool's mark and the call in plain words, a live state while it runs, and the input and output a click away, with approval and retry when needed.
• Agent status: A compact live status pill for a running AI agent: the agent's mark in a live ring, the current activity and an elapsed timer, opening into the steps so far.
• Rating: A simple, accessible way to capture a numeric opinion.

Also in ai

• Agent plan: The plan an agent writes before it acts: edit, reorder or add steps while it is a draft, then watch it work through them as a live checklist.
• Agent timeline: A compact timeline of one orchestrated agent run: the orchestrator and its subagents share a time axis, handoffs draw in between rows, and a playhead replays thinking, tool calls and waiting while the header counts time, tokens and cost. Hover a span for what it did, or click it to trace its handoff path.
• Context window: An AI context window as a grid of 200 cells: the system prompt, tools, files, summary and messages fill it in order, a threshold row marks where compaction starts, and sending a message, attaching a file or compacting shows exactly how much still fits.
• Reasoning block: The collapsible thinking block of an AI reply. While the model thinks, a shimmering label counts the seconds and the latest reasoning streams underneath. When it finishes, it folds to "Thought for 7s" and opens to show the full reasoning as calm steps with headings.
• Source cards: A row of cited sources under an AI answer where cards stream in with real site marks while the model searches, the overflow collapses into a stack of favicons, hovering lifts a preview with the passage, and an inline [n] citation highlights its card.
• Model card: A model details card where switching models rolls every price, limit and score in place, a token slider estimates monthly cost live, and benchmark bars show each model's rank on hover. Compare crossfades to a side-by-side table against any rival with the better values marked, and the card never changes size.
• AI workflow: A Linear-style AI workflow card where a Gmail trigger, a Claude step, a branch and Slack and Linear actions sit on one hairline rail, and a test run glides down it, opening each step's output inline. Steps are added from a compact command menu with real app marks.
• Code suggestion: An AI code edit suggestion where the model's proposed changes stream into a small editor panel as inline diff hunks, and you accept or reject each one, or all at once with Cmd+Enter. Accepted hunks fold into the file with a smooth height change.
• Ghost text: An inline AI autocomplete where muted ghost text continues your sentence exactly at the caret and Tab turns it solid in place. Cmd+Right takes it one word at a time, Escape fades it away, and a calm chip shows the model behind it.
• Image generation: An image generation card where four images resolve as a pixel mosaic, from coarse colour blocks to full detail under a soft shimmer, each with its own progress ring. Pick one to upscale with a sweeping pixel band, vary or download it, with real provider marks and a built-in simulation.
• Dictation button: A chat composer with voice input, where the mic springs into a recording pill with a smooth live waveform, a timer, and cancel and insert buttons. Words stream into the field as you speak, muted until the recognizer settles them.
• Speech player: A read-aloud player for AI replies. The Read aloud button in the message's action row turns into a compact player with play, a scrubbable progress bar, speed and a voice picker, and a highlight follows the spoken word through the reply, karaoke style.
• Meeting summary: An AI meeting notes card: the header shows the Google Meet or Zoom mark, the attendees and the duration. Summary, Decisions and Action items stream in after a short summarizing pass. Hover any line to see the transcript quote it came from, then check off action items or send them to Linear or Notion.
• Reply draft: An AI email reply drafter where Claude streams a reply under a received Gmail message. Quick replies steer a fresh draft, tone and length rewrite it with a single crossfade, and you can edit the finished draft before you insert it.
• Agent handoff: A support conversation where an AI assistant hands off to a person. When it transfers, a card shows the summary it passes to the team and the typical wait. The person then joins and takes over, and a thin timeline on the left marks each step.
• PII redaction: A guardrail card where personal data is redacted before the prompt reaches the model. Scan marks each name, email, phone number and card with its type and swaps it for a placeholder like [EMAIL_1]. The safe prompt travels to Claude, and the reply comes back with the original values put back for the person.
• LLM cost calculator: A pricing calculator for LLM workloads. Set tokens per request, requests per day and prompt caching, and eight current models re-rank by monthly cost. Bars glide and prices roll as you drag.
• Provider keys: A settings card for bring-your-own-key AI products. Each provider row shows its real mark, the masked key, a status and when the key was last used. You can reveal a key for five seconds, copy, rotate or remove it with undo. Adding or rotating a key opens an inline form that checks the format as you type, then tests the connection before saving.
• Generation stats: A live stats strip for a streaming LLM response where time to first token, speed with a sparkline, output tokens and cost count up in tabular numerals beside the model's real mark, then settle and open into a latency and token cost breakdown.
• AI translate: A message card where picking a language streams the AI translation in place, sentence by sentence over the dimmed original, with a detected-language chip, a Show original toggle and a status line credited to the model's mark.
• TL;DR toggle: An article card with a Full, Summary and Key points switch and a length slider. Switching streams an AI summary in place of the article as the card's height springs to fit, and each key point links back to the paragraph it came from, which gets scrolled to and highlighted.
• Connector setup: A "Connect your tools" card for an AI assistant. Each app connects inline: it redirects, authorizes and runs a first sync with a progress hairline, then lists the scopes it was granted and offers Disconnect with an inline confirm.
• Smart form fill: A paste-to-fill form card where AI reads an email signature or messy notes and fills a contact field by field. Each value flashes in with a confidence dot, its source lights up in the pasted text, low-confidence guesses ask for review, and Undo puts the old values back.
• Enrich column: An AI enrichment column for a data table, where one prompt runs down every row and each cell shimmers while it works, then settles into a value with its source or a failure you can retry.
• Ticket router: A support ticket router where messages from Gmail, Intercom, Slack and Zendesk come in one at a time. An AI classifier labels each one with intent, sentiment and confidence, and the ticket moves into a team lane with an assignee. Low confidence tickets wait in a review lane, and one click there routes them to the suggested team.
• Ask your data: A natural language to chart card: you ask a question, PostgreSQL streams into a collapsible, syntax highlighted panel, the query runs with a rolling row count, and the answer builds as stacked bars, lines or a table, with a one line insight streamed in underneath.
• Agent cursor: A live document where Claude edits like a collaborator. Its labeled cursor comes out of its avatar, selects a paragraph and streams in a rewrite, adds a heading and fixes a typo, while a teammate's cursor reads along. Changes stay tinted until someone accepts or undoes them from a floating review bar.
• Provider status: A status card for the AI providers your product depends on. Each row shows the provider's real mark, its health as an icon and label, p50 latency and a 30-day uptime bar with a tooltip for each day. An incident row expands into its timeline of updates, and the card checks again on a visible countdown.
• Training run: A fine-tuning job card where a live train and validation loss curve draws across a fixed step axis that doubles as the epoch progress bar. It shows the learning rate, elapsed time, ETA and the latest evals and checkpoints, has Pause and Cancel while it runs, and ends in results with a Deploy button.
• AI command: A Cmd+K command palette with an AI mode. Search pages and actions, or press Tab to ask a question: the answer streams inside the palette with numbered sources, and the next steps it suggests, like filing a Linear issue or opening a Notion doc, run straight from the list.
• Starter prompts: A greeting and a grid of starter cards for the empty state of an AI app. The cards are grouped into Write, Code, Analyze and Plan tabs, and a shuffle swaps them with a short staggered crossfade. Picking a card fills the composer, and cards that use a connected app show its mark (Gmail, GitHub, Notion, Linear, Google Calendar).
• AI mascot: A small assistant character, a soft pebble with pill eyes and a companion dot, that shows what the AI is doing. It breathes and glances when idle, leans in to listen, looks up while the dot orbits its head, reads along the line it writes, squints with a sparkle when done and shakes once with worried brows on an error.
• Image reveal: An image generation canvas where a soft, blurred preview made from the image's own colors sharpens top to bottom behind a soft-edged band. It works the way ChatGPT, Midjourney and Gemini show images forming, with fine film grain, a translucent progress pill and calm queued and error states.
• AI spark: A brand-quality animated spark mark. Four tapered rays and four lighter diagonals breathe at rest, ripple while thinking, pulse like a heartbeat while writing, then gather and settle when done. Every status change blends from the pose the mark is already in.
• Pixel mascot: A pixel-art robot that shows what an AI assistant is doing. It idles, thinks, types, celebrates and errors in frame-stepped sprite animations, and stays crisp at every integer size from 24px to 192px.
• Ghost mascot: A floating ghost mascot whose soft sheet ripples at the hem while it hovers. It blinks when idle, turns toward you to listen, fades a little translucent while thinking, draws a tiny pen line while writing, smiles with a sparkle when done and wobbles once on an error.
• Cube mascot: An isometric cube mascot where three shaded faces and a painted-on face show what the assistant is doing. It turns a quarter turn in eased steps while thinking, prints lines onto the floor while writing, settles with a sparkle when done, and shakes once on error.
• Tone tuner: A brand voice card where two sliders (formality and detail) and Friendly, Confident and Empathetic chips rewrite a customer reply. Each changed sentence crossfades in place, new words can be highlighted against the original, and Copy takes the current version.
• Upgrade prompt: An upgrade nudge for the moment someone hits a limit. It shows a usage meter at 50 of 50 AI credits, a rolling price with a monthly and yearly toggle, three concrete unlocks with real model marks, and Upgrade or Maybe later. Upgrading leads into a success state with the new limits, and the card never changes size between states.
• Referral card: A give-and-get referral card where people copy or share their invite link, invite friends by email as chips, and watch invites move from invited to signed up to earned, with the credit total counting up and a milestone reward unlocking.
• Trial banner: A trial status banner where a ring counts down the days left, the copy names what the workspace loses, and the upgrade path is one click away. It comes as a slim banner, a sidebar card or a header pill. It shifts to a warning tone in the last days, has expired and upgraded states, and folds into the pill when dismissed or snoozed.
• Team switcher: A workspace switcher like Linear, Vercel or Slack. The trigger shows the current workspace's logo and plan. The menu has search, your role in each workspace and a Cmd+1 to 9 shortcut for each, and lets you create or join a workspace inline. A highlight glides between rows, and switching crossfades the trigger through a short loading state.
• Live visitors: A realtime visitors card where the live count rolls digit by digit, new arrivals ping in on a dotted world map, the top pages reorder with bars, and signups and upgrades tick in with country flags.
• Social proof toast: A stack of social proof notifications for landing and pricing pages, where recent trials, upgrades and verified purchases from people and companies arrive every few seconds. The stack pauses and fans out on hover, and visitors can dismiss any toast.
• Install snippet: A "get started in 30 seconds" card where framework tabs, three numbered steps and highlighted snippets take a developer from install to first event. Generate key wipes a fresh API key into the placeholder in place.

Guidance for AI tools

Response feedback: A feedback control for AI replies where thumbs down opens an inline panel with reason chips and an optional note, thumbs up fills and asks what was good, and a submit shows a short thank-you before folding back into the row. Follow the declared prop types and do not invent props. Keep keyboard access, reduced motion support, and both light and dark themes intact when adapting it.

Full library index: https://ui.xzero.co.uk/llms.txt