Autonomous AI agents can read requests, retrieve data, reason through options, and trigger actions in seconds. That speed is useful, but it also creates risk when the next step affects money, customer records, or external systems.

Human-in-the-loop checkpoints add control at the moment an agent’s recommendation is about to become a real-world action. In this article, we’ll build a LangGraph refund agent that investigates a request, proposes a refund, pauses for human approval, and only executes the action after review.

Table of contents

What Is a Human-in-the-Loop Checkpoint?

When Should an Agent Ask for Approval?

How the Refund Agent Workflow Works

Prerequisites

Create Mock Order Data

Create the Order Lookup Tool

Define the Refund Proposal Structure

Create the LLM and Build the Refund Agent

Run the Agent Investigation

Convert the Investigation into a Structured Refund Proposal

Create the Refund Tool

Define the LangGraph State

Create the Agent Node

Add the Human Approval Checkpoint

Route the…