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
Pause a tool with Strands' native interrupt
AWS Strands ships a first-class
interrupt primitive.
A tool declared with @tool(context=True) calls
tool_context.interrupt(name, reason=...), which halts the agent loop and
hands reason to the client as the interrupt payload. The AG-UI adapter
finishes the run with RUN_FINISHED carrying outcome.type == "interrupt".
@tool(context=True)
def schedule_meeting(topic: str, tool_context: ToolContext, attendee: str = "") -> str:
"""Ask the user to pick a meeting time, then confirm what was scheduled.
Args:
topic: Short description of the meeting purpose.
attendee: Who the meeting is with, if known.
"""
answer = tool_context.interrupt(
"schedule_meeting",
reason={"topic": topic, "attendee": attendee},
)
# Neither the envelope nor the value inside it is guaranteed to be a
# mapping: `ag_ui_strands` wraps a resolved answer as `{"response": ...}`
# and a cancel as `{"cancelled": True}`, but the payload itself is whatever
# the client sent, and a client that answers with a bare value would make
# `answer.get` raise inside the tool. Both levels are checked.
envelope: Mapping = answer if isinstance(answer, Mapping) else {}
# `ag_ui_strands` wraps the answer under "response"; a bridge that passes
# the client payload through (the published TypeScript one does) hands the
# payload itself, so a mapping without that key IS the payload.
inner = envelope["response"] if "response" in envelope else envelope
payload = inner if isinstance(inner, Mapping) else {}
cancelled = (
envelope.get("cancelled")
or envelope.get("status") == "cancelled"
or payload.get("cancelled")
or payload.get("status") == "cancelled"
)
if cancelled:
return f"User cancelled. Meeting NOT scheduled: {topic}"
label = payload.get("chosen_label") or payload.get("chosen_time")
if not label:
return f"User did not pick a time. Meeting NOT scheduled: {topic}"
return f"Meeting scheduled for {label}: {topic}"
The resume payload arrives wrapped: an answer as {"response": ...}, a
client-side cancel as {"cancelled": True}. The adapter wraps it because
Strands' resume gate is truthiness-based, so a bare falsy answer would
re-raise the same interrupt forever.
Keep the pausing tool off a client-executed name
useHumanInTheLoop registers its tool on the FRONTEND, so a name used
there cannot also be a pausing backend tool. This showcase mounts a
dedicated interrupt agent and points the interrupt demos' agent names at
it, leaving schedule_meeting on the shared agent free for the
frontend-tool flow.
Resume in the same process, or across a restart
Pause and resume on the same running process need no extra wiring. For a
resume that survives a restart, give the agent a Strands SessionManager
through StrandsAgentConfig.session_manager_provider; the adapter
persists its interrupt checkpoint into that session.
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?