Back to Copilotkit

A2UI

showcase/shell-docs/src/content/docs/generative-ui/a2ui.mdx

1.57.03.2 KB
Original Source

What is this?

A2UI (Agent-to-UI) is a declarative Generative UI specification, led by Google with CopilotKit as a launch and design partner. It lets your agent render structured UI components through a JSON-based schema instead of plain text: cards, rows, columns, badges, and price tags, all composed from a catalog of components you (or the platform) define.

You can design and preview A2UI schemas visually using the A2UI Composer.

The two approaches

CopilotKit ships two complementary A2UI approaches:

  • Dynamic Schema — a secondary LLM generates both the schema and the data. Maximum flexibility — the agent can produce any UI for any prompt.

  • Fixed Schema — the component tree is authored ahead of time as JSON. The agent only streams data into the data model at runtime. Fastest — no LLM schema generation.

Both approaches share the same A2UI wire protocol and the same frontend renderer. The difference is where the schema comes from and how data reaches the client.

How it works

Every A2UI surface is assembled from three kinds of operations emitted by the agent and consumed by the frontend renderer:

  1. createSurface / surfaceUpdate — declares (or pins) the component tree (the schema) for a surface.
  2. updateComponents / dataModelUpdate — supplies the data that populates the components via JSON Pointer paths.
  3. beginRendering — tells the client the first frame is ready.

The CopilotKit Python SDK provides helpers for each:

python
from copilotkit import a2ui

a2ui.create_surface(surface_id, catalog_id=...)
a2ui.update_components(surface_id, components)
a2ui.update_data_model(surface_id, {"items": data})
a2ui.begin_rendering(surface_id, root_id)
a2ui.render(operations=[...])  # wraps and serializes for a tool result

Setup

Enable A2UI in your CopilotRuntime by adding a2ui: true, or pass an object to customise. The middleware handles the wire protocol automatically, intercepting tool results containing A2UI operations and rendering them as rich surfaces in the chat:

typescript
import { CopilotRuntime } from "@copilotkit/runtime";

// Simple — enable with defaults (good for fixed-schema flows)
const runtime = new CopilotRuntime({
  agents: { default: myAgent },
  a2ui: true,
});

// Or customise — e.g. auto-inject the render tool for dynamic schemas
const runtime = new CopilotRuntime({
  agents: { default: myAgent },
  a2ui: {
    injectA2UITool: true,
  },
});
<Callout type="warn"> Without `a2ui` configured on the CopilotRuntime, A2UI surfaces will not render — the operations will fall through as plain tool results. </Callout>

Choose your approach

<Cards> <Card title="Dynamic Schema" href="./a2ui/dynamic-schema" description="A secondary LLM generates both the schema and data. Any UI from any prompt." /> <Card title="Fixed Schema" href="./a2ui/fixed-schema" description="Pre-authored JSON schema, agent streams data. Fastest path to production-quality UI." /> </Cards> <IntegrationGrid path="generative-ui/a2ui" />