Skip to content

Human-in-the-loop

LangGraph supports robust human-in-the-loop (HIL) workflows, enabling human intervention at any point in an automated process. This is especially useful in large language model (LLM)-driven applications where model output may require validation, correction, or additional context.

Key capabilities

  • Persistent execution state: LangGraph checkpoints the graph state after each step, allowing execution to pause indefinitely at defined nodes. This supports asynchronous human review or input without time constraints.

  • Flexible integration points: HIL logic can be introduced at any point in the workflow. This allows targeted human involvement, such as approving API calls, correcting outputs, or guiding conversations.

Typical use cases

  1. 🛠️ Reviewing tool calls: Humans can review, edit, or approve tool calls requested by the LLM before tool execution.
  2. ✅ Validating LLM outputs: Humans can review, edit, or approve content generated by the LLM.
  3. 💡 Providing context: Enable the LLM to explicitly request human input for clarification or additional details or to support multi-turn conversations.

Implementation

  • interrupt function: Pauses execution at a specific point, presents information for human review.
  • Command primitive: Used to resume execution with a value provided by the human.