# Interactive components

> Create approval flows where the agent pauses and waits for human input.

> **Not available for Langchain DeepAgents yet.** The code on this page comes from the showcase's `gen-ui-interrupt` demo, and Langchain DeepAgents doesn't have it yet. See this page for [CopilotKit's Built-in Agent](/generative-ui/interactive), [LangGraph (Python)](/langgraph-python/generative-ui/interactive), [LangGraph (TypeScript)](/langgraph-typescript/generative-ui/interactive).

## What is this? [#what-is-this]

Interactive generative UI creates flows where the agent pauses execution and waits for user input before continuing. This enables approval workflows, confirmation dialogs, and any scenario where human judgment is needed mid-execution.

## When should I use this? [#when-should-i-use-this]

Use interactive generative UI when you need:

- Approval/rejection flows (e.g. "Run this command?")
- User decisions that the agent should know about
- Confirmation dialogs with structured responses
- Any flow where the agent pauses for human judgment

## How it works in code [#how-it-works-in-code]

Deep Agents compile to LangGraph graphs, so they support both patterns.
`CopilotKitMiddleware` forwards a `useHumanInTheLoop` tool to the model, the
same way it forwards any frontend tool. For `useInterrupt`, call LangGraph's
native `interrupt()` from a middleware hook. Deep Agents has no live demo on
these pages yet, so the steps below carry the code.

<Steps>
  <Step>
    ### Call `interrupt` from a middleware hook

    A Deep Agent has no custom nodes, so put the pause in a middleware hook.
    This hook runs before the model call and asks the user to name the agent
    the first time. The middleware also declares the `agent_name` state field
    that stores the answer.

    <Tabs groupId="agent_language" items={['Python', 'TypeScript']} persist>
      <Tab value="Python">
        ```python title="agent.py"
        from typing import Any, NotRequired

        from copilotkit import CopilotKitMiddleware, CopilotKitState
        from deepagents import create_deep_agent
        from langchain_openai import ChatOpenAI
        from langchain.agents.middleware import AgentMiddleware
        from langgraph.runtime import Runtime
        from langgraph.types import interrupt

        class AgentState(CopilotKitState):
            agent_name: NotRequired[str]

        class AgentNameMiddleware(AgentMiddleware[AgentState, Any]):
            state_schema = AgentState

            def before_model(self, state: AgentState, runtime: Runtime[Any]) -> dict[str, Any] | None:
                if not state.get("agent_name"):
                    # Interrupt and wait for the user to respond with a name
                    name = interrupt("Before we start, what would you like to call me?")
                    return {"agent_name": name}
                return None

        agent = create_deep_agent(
            model=ChatOpenAI(model="gpt-6-luna", reasoning_effort="none"),
            middleware=[
                AgentNameMiddleware(),
                CopilotKitMiddleware(expose_state=["agent_name"]),
            ],
            system_prompt=(
                "You are a helpful assistant. After the user chooses a name, "
                "Current agent state contains agent_name. Use that value as your own name."
            ),
        )
        ```
      </Tab>
      <Tab value="TypeScript">
        ```ts title="agent.ts"
        import {
          createCopilotkitMiddleware,
          zodState,
        } from "@copilotkit/sdk-js/langgraph";
        import { createMiddleware } from "langchain";
        import { createDeepAgent } from "deepagents";
        import { interrupt } from "@langchain/langgraph";
        import { z } from "zod";

        const agentNameMiddleware = createMiddleware({
          name: "AgentState",
          stateSchema: z.object({
            // zodState keeps this custom field in AG-UI state snapshots.
            agentName: zodState(z.string().optional()),
          }),
          beforeModel: (state) => {
            if (!state.agentName) {
              // Interrupt and wait for the user to respond with a name
              const name: string = interrupt("Before we start, what would you like to call me?");
              return { agentName: name };
            }
          },
        });

        const stateAwareCopilotKitMiddleware = createCopilotkitMiddleware({
          exposeState: ["agentName"],
        });

        export const agent = createDeepAgent({
          model: "openai:gpt-6-luna",
          middleware: [
            agentNameMiddleware,
            stateAwareCopilotKitMiddleware,
          ],
          systemPrompt:
            "You are a helpful assistant. After the user chooses a name, " +
            "Current agent state contains agentName. Use that value as your own name.",
        });
        ```
      </Tab>
    </Tabs>

  </Step>
  <Step>
    ### Make the agent aware of the answer

    Resuming an interrupt and telling the model about the answer are separate
    steps. By default the model is not aware of the interaction: the run
    resumes, and the model never sees what the user chose.

    The custom middleware saves the answer in thread state. In TypeScript,
    `zodState` also keeps the custom field in the graph's output, so AG-UI can
    send it to the frontend. The CopilotKit middleware then adds only the
    allowlisted field (`expose_state` / `exposeState`) to each model request,
    and the system prompt says what that field means. State exposure is off by
    default, so without the allowlist the model never sees the name. Keep the
    allowlist narrow, and do not expose unrelated application state.

  </Step>
  <Step>
    ### Handle the interrupt in your frontend

    Give `useInterrupt` a component to render, and call `resolve` with the
    user's answer. Whatever you pass to `resolve` becomes the return value of
    `interrupt()`.

    ```tsx title="app/page.tsx"
    import { useInterrupt } from "@copilotkit/react-core/v2";
    // ...

    const YourMainContent = () => {
      // ...
      // styles omitted for brevity
      useInterrupt({
        render: ({ event, resolve }) => (
          <div>
            <p>{event.value}</p>
            <form onSubmit={(e) => {
              e.preventDefault();
              resolve((e.target as HTMLFormElement).response.value);
            }}>
              <input type="text" name="response" placeholder="Enter your response" />
              <button type="submit">Submit</button>
            </form>
          </div>
        )
      });
      // ...

      return <div>{/* ... */}</div>
    }
    ```

    The AG-UI LangGraph adapter sends an object interrupt value as a JSON
    string, so parse `event.value` before you read fields from it.

    When your app already selects an agent in its `CopilotKit` provider,
    `useInterrupt` uses that agent. Pass `agentId` only when this component
    must target a different agent in a multi-agent app.

  </Step>
</Steps>

On the frontend, register an interrupt renderer with `useInterrupt`. When the
agent pauses, your component mounts inline in the chat, captures the user's
choice, and resumes the run with that input. The excerpt imports the demo's
`TimePickerCard`, its fallback slots, and its suggestions. Use your own picker
component in their place.

On the backend, the agent pauses the run with its framework's interrupt
primitive and waits for the user's answer before it continues.

Ask the agent to book a call, for example `Book an intro call with the sales
team to discuss pricing`. The time picker appears in the chat. Pick a slot,
and the agent confirms the booked time.

<IntegrationGrid path="human-in-the-loop" />
