HITL Overview
Allow your agent and users to collaborate on complex tasks.
Not available for agent-spec yet
hitl-in-chat demo, and agent-spec doesn't have it yet. See this page for CopilotKit's Built-in Agent, LangGraph (Python), LangGraph (TypeScript).See this in Inspector
Open Inspector on localhost. Go to Inspect, then Frontend Tools. Your tool and its schema are listed.
More detail: Inspector.
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 input: the agent needs a value only the user knows, such as a meeting time.
- Risky actions: the agent must get a yes before it sends, pays, or deletes.
- Expert input: the user supplies domain knowledge the model lacks.
Two patterns for HITL in CopilotKit
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 your agent emits, for example LangGraph interrupt() or Mastra suspend() |
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.
Use useHumanInTheLoop with Agent Spec
Agent Spec agents have no interrupts, so useInterrupt does not apply. A
human-in-the-loop step in Agent Spec is a frontend tool: the agent declares
it as a ClientTool, and the browser renders it with useHumanInTheLoop.
Open Agent Spec has no live demo on these pages yet, so the steps below carry the code.
Create a frontend human-in-the-loop tool
Register the tool with useHumanInTheLoop. Its render shows two
buttons, and the user's click becomes the tool result. In this example,
the agent offers two options and waits for the user to pick one.
import { useHumanInTheLoop } from "@copilotkit/react-core/v2"
import { z } from "zod"
export function Page() {
// ...
useHumanInTheLoop({
name: "offerOptions",
description: "Give the user a choice between two options and have them select one.",
parameters: z.object({
option_1: z.string().describe("The first option"),
option_2: z.string().describe("The second option"),
}),
render: ({ args, respond }) => {
if (!respond) return <></>;
return (
<div>
<button onClick={() => respond(`${args.option_1} was selected`)}>{args.option_1}</button>
<button onClick={() => respond(`${args.option_2} was selected`)}>{args.option_2}</button>
</div>
);
},
});
// ...
}Declare the tool in your agent
Declare the same tool as a ClientTool in your Agent Spec config. The
name must match the name in useHumanInTheLoop:
from pyagentspec.property import Property
from pyagentspec.tools import ClientTool
offer_options_tool = ClientTool(
name="offerOptions",
description="Give the user a choice between two options and have them select one.",
inputs=[
Property(title="option_1", json_schema={"title": "option_1", "type": "string"}),
Property(title="option_2", json_schema={"title": "option_2", "type": "string"}),
],
)Add offer_options_tool to the tools list of your Agent. The agent
declares the tool, and the browser runs it.
Try it out
Ask: Can you show me two good options for a restaurant name? The two
options appear as buttons in the chat. After you pick one, the agent
continues with your choice.
Pattern 1: useHumanInTheLoop (tool-based)
Register a HITL tool in your React app with useHumanInTheLoop.
When the LLM calls that tool, CopilotKit routes the call through your
render function, which shows a custom component and calls respond
with the user's answer. The agent sees the answer as the tool result and
continues from there.
The sample imports TimePickerCard from its own file. The card renders the
slots and calls onSubmit with the user's choice. These are its props:
Each slot button calls onSubmit({ chosen_time: s.iso, chosen_label: s.label }).
The "None of these work" button calls onSubmit({ cancelled: true }). The full
file is in the Code view of the demo at the top of this page.
The picker UI is fed a static list of candidate slots. This is just data the demo page owns, so you can swap in real availability, a calendar API, or anything else:
Pattern 2: useInterrupt (agent-paused)
With an interrupt, your agent code enforces the pause, for example with
LangGraph's interrupt():
- A node calls
interrupt({...}), and the run stops. - The client receives the payload and renders your UI.
- The user answers, and the run resumes with the answer.
CopilotKit's useInterrupt hook is the render contract.
See the useInterrupt deep dive for
the full walkthrough, including the backend tool and render-prop wiring.
Going headless
Both patterns above ship with a render prop. CopilotKit handles the
"when to show the picker" logic for you. If you want to drive
interrupt resolution from a custom UI that lives anywhere in the tree
(not necessarily inside a chat), see the
headless interrupts guide. It shows
how to compose useAgent, agent.subscribe, and copilotkit.runAgent
to build your own useInterrupt equivalent.
How is this guide?