Dynamic Schema A2UI

LLM-generated A2UI — a secondary LLM creates both the schema and data from any prompt.

"""Agno agent for the Declarative Generative UI (A2UI Dynamic Schema) demo.Mirrors the langgraph-python `a2ui_dynamic.py` pattern: the agent owns the`generate_a2ui` tool explicitly. When called, it invokes a secondaryOpenAI client bound to `render_a2ui` (tool_choice forced) using theregistered client catalog injected via the runtime's`state.copilotkit.context`. The tool result returns an `a2ui_operations`container which the runtime's A2UI middleware detects and forwards to thefrontend renderer.Why a separate agent (vs reusing the main agent's `generate_a2ui` tool)?The main agent uses a hardcoded internal catalog ID(`copilotkit://app-dashboard-catalog`) and ignores any runtime catalog thefrontend registers via `<CopilotKit a2ui={{ catalog }}>`. This dedicatedagent reads the runtime catalog from `session_state["copilotkit"]["context"]` so it stays in sync with the frontend renderer's catalog.The dedicated runtime route (`api/copilotkit-declarative-gen-ui/route.ts`)sets `injectA2UITool: false` so the runtime does not double-bind a secondA2UI tool on top of this one."""from __future__ import annotationsimport jsonimport openaifrom agno.agent.agent import Agentfrom agno.models.openai import OpenAIChatfrom agno.run import RunContextfrom dotenv import load_dotenvfrom tools import (    build_a2ui_operations_from_tool_call,    RENDER_A2UI_TOOL_SCHEMA,)load_dotenv()SYSTEM_PROMPT = (    "You are a demo assistant for Declarative Generative UI (A2UI — Dynamic "    "Schema). Whenever a response would benefit from a rich visual — a "    "dashboard, status report, KPI summary, card layout, info grid, a "    "pie/donut chart of part-of-whole breakdowns, a bar chart comparing "    "values across categories, or anything more structured than plain text — "    "call `generate_a2ui` to draw it. The registered catalog includes "    "`Card`, `StatusBadge`, `Metric`, `InfoRow`, `PrimaryButton`, `PieChart`, "    "and `BarChart` (in addition to the basic A2UI primitives). Prefer "    "`PieChart` for part-of-whole breakdowns (sales by region, traffic "    "sources, portfolio allocation) and `BarChart` for comparisons across "    "categories (quarterly revenue, headcount by team, signups per month). "    "`generate_a2ui` takes a single `context` argument summarising the "    "conversation. Keep chat replies to one short sentence; let the UI do "    "the talking.")def generate_a2ui(run_context: RunContext, context: str) -> str:    """Generate dynamic A2UI components based on the conversation.    A secondary LLM designs the UI schema and data. The result is    returned as an `a2ui_operations` container for the A2UI middleware    to detect and forward to the frontend renderer.    The runtime A2UI middleware injects the registered client catalog    schema into `state.copilotkit.context` automatically. We pull it out    of the per-run `session_state` (Agno's `validate_agui_state` mirrors    `RunAgentInput.state` into `session_state`) so the secondary LLM    knows which components are available — staying in sync with the    frontend catalog.    Args:        run_context: Agno run context (provides session_state).        context (str): Conversation context summary the secondary LLM            should design UI from.    Returns:        str: A2UI operations as JSON.    """    state = getattr(run_context, "session_state", None) or {}    context_entries = []    if isinstance(state, dict):        ck = state.get("copilotkit") or {}        if isinstance(ck, dict):            entries = ck.get("context") or []            if isinstance(entries, list):                context_entries = entries    context_text_parts: list[str] = []    for entry in context_entries:        if isinstance(entry, dict):            value = entry.get("value")            if isinstance(value, str) and value:                context_text_parts.append(value)    catalog_context = "\n\n".join(context_text_parts)    system_prompt = (        catalog_context if catalog_context else "Generate a useful dashboard UI."    )    if context and context.strip():        system_prompt = f"{system_prompt}\n\nConversation context:\n{context}"    client = openai.OpenAI()    response = client.chat.completions.create(        model="gpt-4.1",        messages=[            {"role": "system", "content": system_prompt},            {                "role": "user",                "content": (                    "Generate a dynamic A2UI dashboard based on the conversation."                ),            },        ],        tools=[            {                "type": "function",                "function": RENDER_A2UI_TOOL_SCHEMA,            }        ],        tool_choice={            "type": "function",            "function": {"name": "render_a2ui"},        },    )    choice = response.choices[0]    if choice.message.tool_calls:        args = json.loads(choice.message.tool_calls[0].function.arguments)        result = build_a2ui_operations_from_tool_call(args)        return json.dumps(result)    return json.dumps({"error": "LLM did not call render_a2ui"})agent = Agent(    model=OpenAIChat(id="gpt-4o", timeout=120),    tools=[generate_a2ui],    tool_call_limit=4,    description=SYSTEM_PROMPT,)

In the dynamic-schema approach, a secondary LLM generates the entire UI (schema, data, and layout) based on the conversation context. It's the most flexible A2UI flavor; the agent can render any UI for any request without pre-defined schemas.

How it works#

The primary LLM decides to call render_a2ui (the tool the runtime auto-injects when injectA2UITool: true).
The runtime serializes your client-side catalog (component names + Zod prop schemas) into the agent's copilotkit.context so the LLM knows which components it may emit.
The tool call streams through LangGraph as TOOL_CALL_ARGS events.
The A2UI middleware intercepts the stream and renders cards progressively as data items arrive.

The 3-file split#

The canonical Bring-Your-Own-Catalog (BYOC) layout keeps three files side-by-side under frontend/src/app/a2ui/:

File	What lives there
`definitions.ts`	Zod props schema + human-readable descriptions for each custom component. Platform-agnostic, so the runtime can serialise it to the LLM.
`renderers.tsx`	React implementations keyed by the same names. TypeScript enforces that every definition has a renderer.
`catalog.ts`	`createCatalog(definitions, renderers, { includeBasicCatalog: true })`: merges your custom components with CopilotKit's built-in primitives.

Declare your custom component definitions#

Each entry pairs a Zod prop schema with a description. The description is crucial; the LLM reads it to decide which component to emit. The example below ships a small dashboard catalog (Card / StatusBadge / Metric / InfoRow / PrimaryButton):

definitions.ts

import { z } from "zod";import type { CatalogDefinitions } from "@copilotkit/a2ui-renderer";export const myDefinitions = {  Card: {    description:      "A titled card container with an optional subtitle and a single child slot. Use it to group related content (metrics, rows, buttons).",    props: z.object({      title: z.string(),      subtitle: z.string().optional(),      child: z.string().optional(),    }),  },  StatusBadge: {    description:      "A small coloured pill communicating the state of something (healthy/degraded/down, online/offline, open/closed). Choose `variant` to match the intent.",    props: z.object({      text: z.string(),      variant: z.enum(["success", "warning", "error", "info"]).optional(),    }),  },  Metric: {    description:      "A key/value KPI display with an optional trend indicator. Ideal for dashboards (e.g. 'Revenue • $12.4k • up').",    props: z.object({      label: z.string(),      value: z.string(),      trend: z.enum(["up", "down", "neutral"]).optional(),    }),  },  InfoRow: {    description:      "A compact two-column 'label: value' row. Good for stacks of facts inside a Card (owner, region, last updated, etc.).",    props: z.object({      label: z.string(),      value: z.string(),    }),  },  PrimaryButton: {    description:      "A styled primary call-to-action button. Attach an optional `action` that will be dispatched back to the agent when the user clicks it.",    props: z.object({      label: z.string(),      action: z.any().optional(),    }),  },  PieChart: {    description:      "A pie/donut chart with a brand-coloured legend. Provide `title`, `description`, and `data` as an array of `{ label, value }` objects. Great for part-of-whole breakdowns (sales by region, traffic sources, portfolio allocation).",    props: z.object({      title: z.string(),      description: z.string(),      data: z.array(        z.object({          label: z.string(),          value: z.number(),        }),      ),    }),  },  BarChart: {    description:      "A vertical bar chart built on Recharts. Provide `title`, `description`, and `data` as an array of `{ label, value }` objects. Great for comparing series across categories (quarterly revenue, headcount by team, signups per month).",    props: z.object({      title: z.string(),      description: z.string(),      data: z.array(        z.object({          label: z.string(),          value: z.number(),        }),      ),    }),  },} satisfies CatalogDefinitions;

Implement the React renderers#

Every key in myDefinitions must have a matching renderer. Props are statically typed against the Zod schema, so refactors stay safe:

renderers.tsx

export const myRenderers: CatalogRenderers<MyDefinitions> = {  Card: ({ props, children }) => (    <Card      className="w-full min-w-0 overflow-hidden"      data-testid="declarative-card"    >      <CardHeader>        <CardTitle>{props.title}</CardTitle>        {props.subtitle && <CardDescription>{props.subtitle}</CardDescription>}      </CardHeader>      {props.child && (        <CardContent className="flex flex-col gap-4">          {children(props.child)}        </CardContent>      )}    </Card>  ),  StatusBadge: ({ props }) => (    <Badge      variant={props.variant ?? "info"}      data-testid="declarative-status-badge"    >      {props.text}    </Badge>  ),  Metric: ({ props }) => {    const trend = props.trend ?? "neutral";    const arrow = trend === "up" ? "↑" : trend === "down" ? "↓" : "";    const trendClass =      trend === "up"        ? "text-emerald-600"        : trend === "down"          ? "text-rose-600"          : "text-[var(--foreground)]";    return (      // `flex-1 min-w-[120px]` lets a row of Metrics distribute evenly      // inside the basic catalog's gap-less Row — 3 metrics in a 600px      // card column get ~200px each instead of squishing to content width.      <div        data-testid="declarative-metric"        className="flex flex-1 min-w-[120px] flex-col gap-1"      >        <div className="text-xs font-medium uppercase tracking-wider text-[var(--muted-foreground)]">          {props.label}        </div>        <div          className={`flex items-baseline gap-1.5 text-2xl font-semibold tabular-nums ${trendClass}`}        >          <span>{props.value}</span>          {arrow && <span className="text-base">{arrow}</span>}        </div>      </div>    );  },  InfoRow: ({ props }) => (    // Divider via `border-b last:border-b-0` so the final row doesn't dangle    // a trailing line, regardless of whether the agent wraps these in a    // Column or drops them directly into a Card's child slot.    <div className="flex items-baseline justify-between gap-4 py-2 border-b border-[var(--border)] last:border-b-0 last:pb-0 first:pt-0">      <span className="text-sm text-[var(--muted-foreground)]">        {props.label}      </span>      <span className="text-sm font-medium text-[var(--foreground)] text-right tabular-nums">        {props.value}      </span>    </div>  ),  PrimaryButton: ({ props, dispatch }) => (    <Button      onClick={() => {        if (props.action && dispatch) dispatch(props.action);      }}    >      {props.label}    </Button>  ),  PieChart: ({ props }) => {    const data = props.data ?? [];    const safeData = Array.isArray(data) ? data : [];    const total = safeData.reduce((sum, d) => sum + (Number(d.value) || 0), 0);    return (      // `flex-1 min-w-0` so multiple charts in a basic-catalog Row      // distribute the available width evenly instead of each insisting      // on its content size and overflowing.      <Card        className="w-full flex-1 min-w-0 overflow-hidden"        data-testid="declarative-pie-chart"      >        <CardHeader>          <CardTitle>{props.title}</CardTitle>          <CardDescription>{props.description}</CardDescription>        </CardHeader>        <CardContent className="flex flex-col gap-4">          {safeData.length === 0 ? (            <div className="py-8 text-center text-sm text-[var(--muted-foreground)]">              No data available            </div>          ) : (            <>              <DonutChart data={safeData} />              <div className="flex flex-col gap-2 pt-2">                {safeData.map((item, index) => {                  const val = Number(item.value) || 0;                  const pct =                    total > 0 ? ((val / total) * 100).toFixed(0) : "0";                  return (                    <div                      key={index}                      className="flex items-center gap-3 text-sm"                    >                      <span                        className="inline-block h-2.5 w-2.5 shrink-0 rounded-sm"                        style={{                          backgroundColor:                            CHART_COLORS[index % CHART_COLORS.length],                        }}                      />                      <span className="flex-1 truncate text-[var(--foreground)]">                        {item.label}                      </span>                      <span className="tabular-nums text-[var(--muted-foreground)]">                        {val.toLocaleString()}                      </span>                      <span className="w-10 text-right tabular-nums text-[var(--muted-foreground)]">                        {pct}%                      </span>                    </div>                  );                })}              </div>            </>          )}        </CardContent>      </Card>    );  },  BarChart: ({ props }) => {    const { isNew } = useSeenIndices();    const data = props.data ?? [];    const safeData = Array.isArray(data) ? data : [];    return (      <Card        className="w-full flex-1 min-w-0 overflow-hidden"        data-testid="declarative-bar-chart"      >        {/* Scoped keyframe — no globals.css needed */}        <style>{`          @keyframes barSlideIn {            from { transform: translateY(40px); opacity: 0; }            20% { opacity: 1; }            to { transform: translateY(0); opacity: 1; }          }        `}</style>        <CardHeader>          <CardTitle>{props.title}</CardTitle>          <CardDescription>{props.description}</CardDescription>        </CardHeader>        <CardContent>          {safeData.length === 0 ? (            <div className="py-8 text-center text-sm text-[var(--muted-foreground)]">              No data available            </div>          ) : (            <ResponsiveContainer width="100%" height={260}>              <RechartsBarChart                data={safeData}                margin={{ top: 12, right: 12, bottom: 4, left: -8 }}              >                <CartesianGrid                  strokeDasharray="3 3"                  stroke="var(--border)"                  vertical={false}                />                <XAxis                  dataKey="label"                  tick={{ fontSize: 12, fill: "var(--muted-foreground)" }}                  stroke="var(--border)"                  tickLine={false}                  axisLine={false}                />                <YAxis                  tick={{ fontSize: 12, fill: "var(--muted-foreground)" }}                  stroke="var(--border)"                  tickLine={false}                  axisLine={false}                />                <Tooltip                  contentStyle={CHART_TOOLTIP_STYLE}                  cursor={{ fill: "var(--muted)", opacity: 0.5 }}                />                <Bar                  isAnimationActive={false}                  dataKey="value"                  radius={[6, 6, 0, 0]}                  maxBarSize={48}                  // eslint-disable-next-line @typescript-eslint/no-explicit-any                  shape={                    ((barProps: any) => (                      <AnimatedBar                        {...barProps}                        isNew={isNew(barProps.index as number)}                      />                      // eslint-disable-next-line @typescript-eslint/no-explicit-any                    )) as any                  }                >                  {safeData.map((_, index) => (                    <Cell                      key={index}                      fill={CHART_COLORS[index % CHART_COLORS.length]}                    />                  ))}                </Bar>              </RechartsBarChart>            </ResponsiveContainer>          )}        </CardContent>      </Card>    );  },};

Wire definitions × renderers into a catalog#

createCatalog is what you hand to the provider. Flip includeBasicCatalog: true to merge CopilotKit's built-ins (Column, Row, Text, Image, Card, Button, List, Tabs, …), so the LLM can compose custom + basic components interchangeably:

catalog.ts

import { createCatalog } from "@copilotkit/a2ui-renderer";import { myDefinitions } from "./definitions";import { myRenderers } from "./renderers";export const myCatalog = createCatalog(myDefinitions, myRenderers, {  catalogId: "declarative-gen-ui-catalog",  includeBasicCatalog: true,});

Pass the catalog to the provider#

A single prop (a2ui={{ catalog }}) is all the frontend needs; the provider registers the catalog and wires up the built-in A2UI activity-message renderer:

page.tsx

import React from "react";import { CopilotKit } from "@copilotkit/react-core/v2";import { myCatalog } from "./a2ui/catalog";import { Chat } from "./chat";export default function DeclarativeGenUIDemo() {  return (    <CopilotKit      runtimeUrl="/api/copilotkit-declarative-gen-ui"      agent="declarative-gen-ui"      a2ui={{ catalog: myCatalog }}    >      <div className="flex justify-center items-center h-screen w-full">        <div className="h-full w-full max-w-4xl">          <Chat />        </div>      </div>    </CopilotKit>

Inject the render tool on the runtime#

On the TypeScript runtime, injectA2UITool: true tells CopilotKit to add the render_a2ui tool to the agent's tool list at request time and serialise your client catalog into the agent's copilotkit.context. No backend code to write; the agent can be an empty create_agent(tools=[]):

app/api/copilotkit/route.ts

const runtime = new CopilotRuntime({
  agents: { default: myAgent },
  a2ui: {
    injectA2UITool: true,
  },
});

Progressive streaming#

The secondary LLM's render_a2ui tool call streams through LangGraph as TOOL_CALL_ARGS events. The A2UI middleware:

Waits for the full components array before emitting anything — the schema must be complete before rendering starts.
Extracts surfaceId + root from the partial JSON.
Emits surfaceUpdate + beginRendering once the schema is complete.
Extracts complete items objects progressively and emits a dataModelUpdate for each, so cards appear one by one as data streams in.

A built-in progress indicator shows while the schema is still generating and hides automatically once data items start arriving.

When should I use dynamic schemas?#

You don't know the UI shape ahead of time; the agent decides what to show based on the user's request.
You want to prototype A2UI without committing to a schema file yet.
You're building a conversational dashboard where the layout varies per turn.

If the surface is well-known (e.g. a product card, a flight result), prefer a fixed schema; it's faster, cheaper, and the UI is deterministic.