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
Declare the tool as an external tool
Agno's AG-UI interface does not forward the request's tool definitions to
the model. The model only sees tools declared on the Agent. A tool you
register with useHumanInTheLoop therefore needs a matching declaration
on the agent, marked external_execution=True, with an empty body. Agno
pauses the run, the browser renders your component, and the run resumes
with the user's answer.
The name and the arguments must match the useHumanInTheLoop
registration exactly. The docstring is what the model reads, so describe
when to call the tool there.
from agno.tools import tool
@tool(external_execution=True)
def offerOptions(option_1: str, option_2: str):
"""
Give the user a choice between two options and have them select one.
Args:
option_1: str: The first option
option_2: str: The second option
"""Register the tool on the agent:
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.os.interfaces.agui import AGUI
from tools.frontend import offerOptions
db = SqliteDb(db_file="tmp/agno.db")
agent = Agent(
model=OpenAIChat(reasoning_effort="none", id="gpt-6-luna"),
tools=[offerOptions],
db=db,
description="A helpful assistant that can answer questions and provide information.",
instructions="Be helpful and friendly. Format your responses using markdown where appropriate.",
)
agent_os = AgentOS(agents=[agent], interfaces=[AGUI(agent=agent)])
app = agent_os.get_app()
if __name__ == "__main__":
agent_os.serve(app="main:app", port=8000, reload=True)Give the agent somewhere to store the paused run
Agno stores the paused run before the browser can return the user's
answer, so the Agent that owns the external tool needs a database. An
agent with an external tool and no db cannot resume after the user
answers.
SqliteDb needs sqlalchemy installed:
pip install sqlalchemyA project-relative SQLite file, as above, is fine for local development.
For production, use durable shared storage such as PgDb. An ephemeral
container file cannot resume a run on another instance.
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.
| Pattern | Who decides to pause? | Backend surface |
|---|---|---|
useHumanInTheLoop | The LLM, by calling a registered client-side tool | A frontend-only tool description (Zod schema + render) |
useInterrupt | Your agent code, at a step that must stop for a person | An 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.
<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:
<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:
- The agent interrupts with a serializable payload.
- The run stops.
- The client renders your UI with the payload.
- 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?