AI commandPro

• Type: Component (special)
• Access: Xzero Pro
• Page: https://ui.xzero.co.uk/components/ai-command
• Markdown: https://ui.xzero.co.uk/components/ai-command/markdown
• Source file: registry/components/ai-command/ai-command.tsx
• Dependencies: motion, lucide-react
• Keywords: special, ai, new, command palette, cmd k, command menu, ask ai, ai search, spotlight, raycast, quick actions, streaming answer, citations, sources, keyboard

When to use

• A global Cmd+K in a SaaS app where people both jump to pages and ask questions about their workspace.
• Search that should fall back to an AI answer when nothing matches.
• Answers that lead straight to an action in another tool, like filing a Linear issue or posting to Slack.

When not to use

• A long, multi-turn conversation: use a chat thread.
• Plain navigation with no AI: use command-palette.
• Inline field suggestions while typing in a form: use an autocomplete input.

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/ai-command

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 { AiCommand } from "@/components/xzero/ai-command/ai-command";

// Sample walkthrough
<AiCommand />

// Wired to your app and model
<AiCommand
  items={commands}
  onSelect={item => { router.push(item.id); setOpen(false); }}
  onAsk={async (question, { signal, append, setSources }) => {
    const res = await fetch("/api/ask", { method: "POST", body: JSON.stringify({ question }), signal });
    const { sources, stream } = await readAnswer(res);
    setSources(sources);
    for await (const delta of stream) append(delta);
    return { actions: [{ id: "issue", label: "Create issue in Linear", run: s => createIssue(question, s) }] };
  }}
  onClose={() => setOpen(false)}
  elevated
/>

API reference

AiCommand

A fixed-size command palette with an AI mode. Search pages and actions, or press Tab to ask: the answer streams in place with numbered sources and runnable next steps. With no props it plays a sample walkthrough until someone interacts.

Prop	Type	Default	Description
items	AiCommandItem[]	sample workspace	Pages and actions to search: { id, label, group?, icon?, meta?, shortcut?, keywords?, suggested?, onSelect? }. Rows marked suggested show while the query is empty.
onSelect	(item: AiCommandItem) => void	–	Runs when a page or action is chosen with Enter or a click. Close your dialog or navigate here.
onAsk	(question, { signal, append, setSources }) => Promise<AiCommandAnswer | void>	simulated engine	Answers a question. Stream text with append, show sources early with setSources, and resolve with { text?, sources?, actions? }. Throw to show the error state with Retry. The signal aborts when the person asks again or goes back.
onAction	(action: AiCommandAction, result: string) => void	–	Runs after a suggested action finishes, with the label it ended on (for example "Created ENG-2481").
onSourceSelect	(source: AiCommandSource) => void	–	Runs when a source chip or citation is chosen. Sources with an href open in a new tab instead.
suggestedQuestions	string[]	3 sample questions	Questions offered while Ask AI is open and empty.
model	{ name: string; mark?: ReactNode }	{ name: "Claude Sonnet 5.5" }	The model that answers, shown in the footer, the input and beside each answer.
defaultMode	"search" | "ask"	"search"	Mode on first render.
defaultQuery	string	""	Query on first render.
onModeChange	(mode: "search" | "ask") => void	–	Runs when the palette switches between Search and Ask AI.
onClose	() => void	–	Escape on an empty search. Use it to close the surrounding dialog.
placeholder	{ search?: string; ask?: string }	–	Input placeholders per mode.
thinkingLabel	string	"Searching your workspace"	Status while the model works, before any text arrives.
autoPlay	boolean	true without items and onAsk	Plays a looping walkthrough while on screen. Stops for good on the first real pointer or key press inside, and never runs with reduced motion.
hotkey	boolean	false	Listens for Cmd+K or Ctrl+K on the page and focuses the input.
height	number	392	Height of the results area in px. The palette keeps this size while typing, switching modes and streaming.
elevated	boolean	false	Adds the floating shadow, for use inside a dialog or popover.
className	string	–	Class on the root.
style	CSSProperties	–	Inline styles on the root.
aria-label	string	"Command palette"	Accessible name of the palette.

AiCommandAction

A suggested next step returned with an answer and run in place.

Prop	Type	Default	Description
id (required)	string	–	Stable id.
label (required)	string	–	Row label, such as "Create issue in Linear".
meta	string	–	Quiet detail after the label.
mark	ReactNode	–	16px brand mark or icon.
run	(signal: AbortSignal) => Promise<string | void>	–	Does the work. Resolve with a done label or nothing; throw to show the error state (Enter retries).
runningLabel / doneLabel / errorLabel / doneMeta	string	–	Labels for each state. doneMeta is where a simulated action says nothing was sent.

AiCommandSource

A document the answer cites as [1], [2] in its text.

Prop	Type	Default	Description
id (required)	string	–	Stable id.
title (required)	string	–	Short chip title, such as "billing-api #1893".
description	string	–	Longer text for the tooltip and screen readers.
mark	ReactNode	–	14px brand mark or icon.
href	string	–	Opens in a new tab when chosen.

Keyboard interactions

Keys	Action
Up / Down	Move through results, questions or suggested actions.
Enter	Open the page, run the action, ask the question, or retry a failed answer or action.
Tab	Ask AI about the current query. With an empty query it opens Ask AI with suggested questions; in that state Tab goes back to search.
Escape	From Ask AI, back to search (cancels a streaming answer). In search, clears the query, then calls onClose.
Cmd / Ctrl + K	Focuses the input when hotkey is on.

Accessibility

• The input is a combobox that owns a listbox; the active row is announced through aria-activedescendant, so focus never leaves the input.
• A polite live region announces questions, finished answers, action results and simulated runs ("Simulated, nothing was sent").
• Status is never color alone: running, done and failed actions change both the icon and the label.
• Citations and source chips are buttons with full descriptions as their accessible names; hovering or focusing one highlights its partner.
• The mode toggle uses aria-pressed buttons and keeps input focus.

Motion

• The palette never changes size: the results area has a fixed height and views crossfade in place (100ms out, 160ms in, 2px rise).
• One highlight glides between rows in 130ms and jumps without travel when the list itself changes, so typing never animates.
• Answers stream 3 to 7 words every 34ms, each chunk fading in over 140ms; the view follows the text down unless you scroll up.
• Labels, status icons and footer hints swap with a single crossfade. The done check draws once.
• Reduced motion: no walkthrough, no chunk fades or travel; the answer reveals in large steps and every state stays.
• The walkthrough pauses off screen through IntersectionObserver and restarts from a clean state.

Responsive behavior

• Fills its container up to 680px and holds up at 360px; long labels and meta truncate with an ellipsis, meta first.
• Below 540px the navigate hint hides from the footer; source chips wrap.
• Rows are 40px tall and work with touch; hover only moves the highlight on fine pointers that actually move.

Performance

• Search is a synchronous word match over the items array, fine for a few hundred rows; filter on the server beyond that.
• Streaming appends one span per chunk; the highlight is positioned directly in the DOM without extra renders.
• The walkthrough and its timers stop off screen and on unmount; in-flight answers and actions abort through their signals.

Notes for AI

• Use for a product-wide Cmd+K that can also answer questions; put it inside a dialog with elevated and onClose.
• Return sources before text with setSources so the chips land first, and cite them in the text as [1], [2].
• Give each suggested action a run that takes the AbortSignal; return the created object's name ("Created ENG-2481") as the done label.
• Keep item labels short and put context in meta; use group to section results.
• For a plain command menu without AI, use command-palette instead.

Related

• Command palette: A complete keyboard driven action surface with search, grouped results, and shortcuts.
• 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.
• 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.
• 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).

Also in ai

• 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.
• 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.
• 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.
• 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.
• 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 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

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. 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