[Human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/): LLM should read this page when developing an AI application that requires human intervention, integrating human feedback into its workflow, or implementing multi-turn conversations. This guide covers the use of the interrupt function in LangGraph to pause graph execution and collect human input, enabling human-in-the-loop workflows. It explains various design patterns, such as approving/rejecting actions, editing graph state, reviewing tool calls, and multi-turn conversations. The Command primitive is introduced for resuming graph execution with human input.

