Dashboard Overview
The screen an app opens on: shell, header, KPI row, chart and activity feed — numbers first, shape second, changes last.
The blank thread answered with real starter prompts, the model picker with the three numbers the choice turns on, and the four surfaces a session grows into — attachments, branches, canvas, threads.
app/assistant-chat-page.tsxnpx hoverlab add assistant-chat-page
Or over MCP, from your editor's agent — no account needed.
Free to read, copy and install, for personal and non-commercial projects. Shipping it in client work or a paid product needs Pro ($79 once). The source lands in your repo and stops being ours — no attribution, nothing to upgrade.
A blank thread, the model behind it, and the four surfaces a real session grows into.
Connected to your warehouse, docs and support inbox. Ask in plain language — I will show the query I ran.
Answers cite their sources. Nothing is written back without your approval.
Changing model applies to your next message. Earlier replies in this thread stay as the model that wrote them left them.
q3-renewals.pdf
820 KB · about 14,200 tokens
dashboard-screenshot.png
1.4 MB · uploading 62%
walkthrough.mov
41 MB
Video is not readable by this model. Attach a screenshot or a transcript.
After editing the question
Build me a pricing card, three plans side by side.
Here it is — one heading, one price, one call to action per plan.
Add a monthly / yearly toggle.
Added. The heading says which period is showing rather than only the switch.
A screen reader reads the per-seat note as part of the price.
Moved it out of the price and linked the two with aria-describedby.
You are looking at v2. The assistant's latest answer is about v3 — anything you ask now applies to that one.
export function PriceCard({ plan, annual }) {
// price derived from the period rather than hard-coded
// the heading names the period, so the switch is not
// the only place the state is visible
}Revenue assistant
Connected to Warehouse · gpt-class model
The real page, rendered in your current theme — every section below is a live block, not a screenshot.
Only want one section? Open it and copy that block instead — browse Agent Chat.
/**
* The assistant, as a whole screen rather than a message list.
*
* Every chat UI looks the same in a screenshot and diverges completely the
* moment someone uses it, because the interesting parts are the ones a
* screenshot cannot show: what the blank thread offers, where the files
* you attached went, what happened to the answer you regenerated.
*
* So the running order here is the order a real session goes through, not
* the order the components look best in.
*
* The empty state is first and it is not decorative. A blank thread is the
* highest-abandonment moment in the product — a cursor blinking in a box
* that could accept anything is a worse prompt than no box at all — and
* <ChatEmptyState> answers it with grouped starter prompts rather than a
* slogan.
*
* The model picker sits directly under it because choosing a model is a
* decision made before the first message and almost never after, and it
* carries the three numbers the choice actually turns on. Burying it in a
* settings menu is how people end up paying frontier prices for
* autocomplete.
*
* Attachments, branches and the canvas are the running conversation, in
* increasing order of how far they are from "a list of messages":
*
* attachments what you staged, and what it costs you in context
* branches the answers regenerate would otherwise have thrown away
* canvas the two-pane layout, once an answer becomes an artifact
*
* The thread panel is last, deliberately, and it is the one people expect
* first. It is the navigation *between* conversations, and navigation
* between things is only interesting once there is more than one — putting
* it at the top of this page would frame the product as a filing cabinet.
*/
import * as React from 'react'
import { ChatEmptyState } from '@/components/chat-empty-state'
import { ChatModelPicker } from '@/components/chat-model-picker'
import { ChatAttachmentTray } from '@/components/chat-attachment-tray'
import { ChatMessageBranches } from '@/components/chat-message-branches'
import { ChatArtifactCanvas } from '@/components/chat-artifact-canvas'
import { ChatThreadPanel } from '@/components/chat-thread-panel'
export default function AssistantChatPage() {
return (
<main className="min-h-screen bg-background text-foreground">
<section className="mx-auto w-full max-w-5xl px-6 pb-2 pt-12">
<h1 className="text-2xl font-bold tracking-tight">Assistant</h1>
<p className="mt-1 text-sm text-muted-foreground">
A blank thread, the model behind it, and the four surfaces a real
session grows into.
</p>
</section>
<ChatEmptyState />
<ChatModelPicker />
<ChatAttachmentTray />
<ChatMessageBranches />
<ChatArtifactCanvas />
{/* Navigation between conversations — last, see the note above. */}
<ChatThreadPanel />
</main>
)
}
components/ — each block page has its own copy button.app/assistant-chat-page.tsx. The imports already point at @/components/…, so they resolve with no edits.The component, its props, the design tokens it expects and the command that installs it — as one prompt. Paste it into Claude, Cursor, v0 or ChatGPT and what they build around it will match the rest of the catalog instead of inventing its own system.
The screen an app opens on: shell, header, KPI row, chart and activity feed — numbers first, shape second, changes last.
An agent working inside a real app: a transcript down the middle — reasoning, answer, then the one card that can act — with what it may read and what it noticed demoted to a rail.
A kanban board inside the app shell, with tabs that admit the board is one view among several and a header whose primary action is creating work.
The canonical CRUD list — header, toolbar, sortable table and pagination framed as one panel instead of three stacked cards.
A wizard for the session someone finishes and a checklist for the one they do not, with the only genuinely blocking step in front of both.
Built around the state a search page is in most of the time — empty — so recent queries lead and the facets sit in a sidebar that survives growing to twelve.
One run opened up in the order you would debug it — intent, actions, the retries that are invisible in both, then cost.
The queue, the same queue sorted by how long things have waited, and the policy that decided both — with the policy last so it is not scrolled past forever.
The three states an agent screen usually omits: the wait before the first token, the trace after something broke with retries costed in the open, and the diff it wants a person to accept.
Why the answer said what it said: what is connected, how stale it is, what the query was allowed to see, what fitted in the window and what fell out — plus the failed-search state a debugging tool is most needed in.
Five ways to reach a model without the cursor leaving the sentence — slash menu, inline completion, selection toolbar, action menu, property inspector — and the two surfaces that say where the answer came from.
A table after real people have used it — columns reordered from the keyboard, a selection bar that asks page-or-all, subtotals that survive collapsing, cells edited in place, and the empty state its own filters produced.
The saved view and the comparison window first, because every figure below depends on both — then six charts, none of which load a charting library.
Thresholds with how often each has actually fired, what that produced, where it went — and the digest settings that exist because of the answer.
The flow between an empty product and a useful one, in the order it goes wrong: sample data offered with equal weight, a file, a URL, the column mapping everything stalls on, and an upload that survives the connection dropping.
A profile form where the role options state what they actually change, the avatar crop works from the keyboard, and a navigation guard names the fields it is about to throw away.
The furniture that is on every screen and belongs to none — navbar, mobile drawer, command palette, shortcut sheet, header search, scope switcher, and the two shapes a detail view takes without losing the list.
Backwards from now and forwards from it on one screen — a day-grouped timeline, a month grid where a busy Tuesday never changes the row height, and the state both are in on day one.
What the product looks like while onboarding happens: a tour step anchored to the control it explains, the skeletons of the slowest load it will ever do, and the checklist that outlives both.