---
title: "Interrupt & steer · agent human oversight · Agent Fieldbook"
url: https://agentfieldbook.org/security/oversight/interrupt-steer/
description: "The human can pause, correct or redirect the agent mid-task without restarting it. Steering rather than gating; keeps the human in control of a long-running run."
section: "Security · Human Oversight"
source: Agent Fieldbook — generated from the published page
---

# Interrupt & steer

The human can pause, correct or redirect the agent mid-task without restarting it. Steering rather than gating; keeps the human in control of a long-running run.

Verified against [langchain-ai.github.io](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/)

- [langchain-ai.github.io](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/)

## How it works

## At a glance

| Field | Value |
| --- | --- |
| Mode | HOTL |
| Example | LangGraph interrupts· human steering of long agent runs |

## Basis

## Verified against

- [https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/)

The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.