HITL Overview

Allow your agent and users to collaborate on complex tasks.

What is this?

Human-in-the-loop (HITL) lets an agent pause mid-run to collect input, confirmation, or a choice from the user, then resume with that answer folded back into its reasoning. It's what turns an autonomous workflow into a collaborative one: the agent keeps its context, the user keeps the steering wheel.

When should I use this?

Use HITL when you need:

  • Quality control: a human gate at high-stakes decision points.
  • Missing information: the agent asks the user for a value it cannot find.
  • Expert input: the user supplies domain knowledge the model lacks.

Two patterns for HITL in CopilotKit

Install the Antigravity AG-UI adapter

pip install ag-ui-antigravity google-antigravity

Ask for the human with a frontend tool

The simplest route is an ordinary frontend tool. Register it in the browser with useHumanInTheLoop, or with useFrontendTool and an async handler that resolves once the user has answered. Each run carries that tool definition to the agent, the adapter rebuilds it as a custom Antigravity tool, and when the model calls it the call parks as an awaited coroutine — the SSE response for that run closes, and the adapter resolves the parked call from a later HTTP run with whatever the handler returned. The model receives that value as the tool's real return value, so there is no proxy tool and no fire-and-forget long-running-tool workaround.

Or pause a server tool with experimental_interrupt()

When the backend decides it needs the user, a Python server tool can pause itself on an AG-UI interrupt with the adapter's experimental experimental_interrupt() and carry on with the answer:

from ag_ui_antigravity import experimental_interrupt

async def schedule_meeting(topic: str, attendee: str) -> str:
    """Books a meeting once the user picks a time."""
    answer = await experimental_interrupt(
        "schedule_meeting",
        message=f"Pick a time for {topic}",
        metadata={"topic": topic, "attendee": attendee},
    )
    if not answer.resolved:
        return f"Not scheduled ({answer.status})."
    return f"Scheduled for {answer.payload['chosen_label']}."

The run ends with RUN_FINISHED carrying an interrupt outcome, which useInterrupt renders; the payload the user resolves it with comes back unchanged in answer.payload. answer.status is "resolved", "cancelled" or "abandoned" (the user sent a new message instead).

Name the tool in the agent's instructions

That leaves the agent with one job: knowing the tool exists and when to call it. A model that is never told about book_call will answer in prose and the picker will never mount.

hitl.py
from agents._common import build

HITL_IN_CHAT_PROMPT = (
    "You help users book an onboarding call with the sales team. "
    "When they ask to book a call, call the frontend-provided "
    "`book_call` tool with a short topic and the user's name. "
    "Keep any chat reply to one short sentence."
)


def hitl_in_chat_agent():
    return build(system_instructions=HITL_IN_CHAT_PROMPT)

The frontend tool is dispatched to the browser at most once per turn (deduplicate_tool_calls, on by default), so a model that re-issues the same call after the harness backgrounds it does not ask the user twice.

ask_question is off in this showcase

Antigravity's own ask_question built-in tool — the one primitive that would park on a real AG-UI interrupt — is disabled here with CapabilitiesConfig(enabled_tools=[BuiltinTools.FINISH]). The CopilotKit demos answer a tool call with a ToolMessage, not an interrupt resume, so a turn that parked on ask_question would wait forever. FINISH has to stay enabled: it is how the harness ends a turn.

CopilotKit ships two complementary ways to pause an agent turn and ask the human something. They look similar from the outside (the chat pauses, a custom component appears, the user answers, the run resumes), but they're wired differently on the backend, and each has its own niche.

PatternWho decides to pause?Backend surface
useHumanInTheLoopThe LLM, by calling a registered client-side toolA frontend-only tool description (Zod schema + render)
useInterruptYour agent code, at a step that must stop for a personAn interrupt the agent emits, for example interrupt() in a LangGraph node

Pick useHumanInTheLoop when the pause is an agent-initiated decision (the model chose to ask the user) and you want the picker UI inlined into the normal tool-call flow.

Pick useInterrupt when the pause is a checkpoint in your agent code: the code path always requires a human answer, and the server-side contract is an interrupt. On the Built-in Agent, interrupts are temporarily unavailable, so use useHumanInTheLoop there.

Pattern 1: useHumanInTheLoop (tool-based)

The app registers a HITL tool on the client with useHumanInTheLoop. When the LLM calls that tool, CopilotKit renders your Vue component and gives it a respond callback during the executing phase. The agent sees the answer as the tool result and continues from there.

src/components/MeetingApproval.vue
<script setup lang="ts">
import { z } from "zod";
import { useHumanInTheLoop } from "@copilotkit/vue/v2";
import TimePickerCard from "./TimePickerCard.vue";

useHumanInTheLoop({
  name: "schedule_meeting",
  description: "Ask the user to select a meeting time.",
  parameters: z.object({
    topic: z.string(),
    attendee: z.string(),
  }),
  render: TimePickerCard,
});
</script>

<template><p>Meeting approval tool registered.</p></template>

TimePickerCard.vue receives the tool arguments and a respond callback. respond is defined only while the tool call is executing:

src/components/TimePickerCard.vue
<script setup lang="ts">
const props = defineProps<{
  args: { topic?: string; attendee?: string };
  respond?: (result: unknown) => Promise<void>;
}>();
</script>

<template>
  <section>
    <p>Pick a time for {{ props.args.topic ?? "the meeting" }}</p>
    <button
      :disabled="!props.respond"
      @click="props.respond?.({ chosen_time: '09:00' })"
    >
      Tomorrow at 09:00
    </button>
  </section>
</template>

The picker UI can use static candidate slots, live availability, a calendar API, or any other application data. Mount the registration component beneath CopilotKitProvider so the composable can reach the runtime.

Pattern 2: useInterrupt (graph-paused)

With a runtime interrupt, your agent code enforces the pause:

  1. The agent interrupts with a serializable payload.
  2. The run stops.
  3. The client renders your UI with the payload.
  4. The user answers, and the client resumes the run with the answer.

CopilotKit's useInterrupt composable and CopilotChat's #interrupt slot form the Vue render contract.

See the useInterrupt deep dive for the full walkthrough, including the backend contract and Vue slot wiring.

Going headless

Both patterns above can drive custom UI. For runtime interrupts, set renderInChat: false and use the reactive state returned by useInterrupt; for a frontend-tool pause, let the Promise-returning HITL tool drive application state. See the headless interrupts guide for the interrupt path.

How is this guide?