# Answer Receipts block

> AI chat stage with framed answer receipts on a live dot field

A self contained chat surface floating on an animated dot field. Asks stay bubbles while every reply renders as a framed receipt carrying the run behind it, a tool trace, a metric row or a code patch, with model, latency and token cost in the chrome bar. Streaming, stop, retry, thread switching and a scoped source picker are all live.

- Type: Pro block
- Category: [AI Chat](https://reui.io/blocks/ai-agents/ai-chat.md)
- Page: https://reui.io/blocks/ai-agents/ai-chat/ai-chat-11
- MCP: `get_block("ai-chat-11")`
- Built with: Badge, Bubble, Button, Dropdown Menu, Empty, Field, Frame, Input Group, Item, Kbd, Marker, Message, Message Scroller, Spinner, Toggle Group, Tooltip
- Installs with a ReUI Pro or Ultimate license; setup: https://reui.io/docs/license-setup

## Best for

Replies as Frame receipts with model, latency and token count in the header and a tool trace, figure row or patch summary under the prose

## Agent notes

- `send` ignores the ask and `scopeIds`: every reply settles after `STREAM_MS` as the next `PENDING_REPLIES` entry, whatever was asked
- Replace `TRANSCRIPTS`, `THREADS`, `MODELS` and `SOURCES`; a reply's `payload` kind `trace`, `metrics` or `patch` picks the strip under its prose
- The Attach button in `Composer` has no handler, and the star, ratings and Clear conversation change only local `favorite`, `ratings` and `turns` state

## When not to use

- A transcript with a starter rail, a context window meter and an extended thinking toggle: use [Copilot Shell](https://reui.io/blocks/ai-agents/ai-chat/ai-chat-1.md) (`get_block("ai-chat-1")`)
- A table of a run's MCP tool calls by server, with the refused scope to grant: use [MCP Call Audit](https://reui.io/blocks/ai-agents/agent-activity/agent-activity-4.md) (`get_block("agent-activity-4")`)

## Install

```bash
npx shadcn@latest add @reui/ai-chat-11
```

## About AI Chat blocks

### When to use

- A full page assistant chat, new chat welcome screen or 2 model comparison inside an AI product
- A copilot docked beside the page it works on, or opened from a launcher in the page corner
- Answers that show the work behind them: sources read, tool steps, plans to approve and run cost

### When not to use

- The product layout around the chat: a sidebar of threads, workspaces and account menus: use the [App Shell blocks](https://reui.io/blocks/application/app-shell.md)
- A plain overlay chat panel opened from a button, with suggestion chips and a composer: use the [Sheet blocks](https://reui.io/blocks/application/sheet.md)
- A highlighted snippet with a filename header and copy button, outside any conversation: use [Code Block](https://reui.io/components/code-block.md) (`get_component("code-block")`)

### Agent notes

- Each `AiChat` root sizes itself to the viewport with `h-svh`, or `min-h-svh` in ai-chat-5; give it your layout's height inside an app shell
- Every reply is canned content from the block's data file, played back on `setTimeout` and `setInterval` timers; stream your model's output there instead

Every ReUI item has a twin like this one; the index is https://reui.io/llms.txt. Agents with the ReUI MCP (https://reui.io/docs/mcp) get the same guidance from the getters named above.
