How to add human oversight using interrupts

​When building agentic applications, the model will often propose actions like making a payment, writing a file, sending an email, or modifying a system.
In many cases, you don’t want these actions to run automatically.
You want a human to review and approve before anything executes.

​This is where interrupts shine.

​Interrupts allow you to safely pause an agent’s workflow, request human approval, and resume only when the action has been validated.

​Join us for our next LangChain Community Kenya monthly meetup as we deep dive into:

• ​What interrupts are

• ​How LangGraph implements them under the hood

• ​How to use them to add human oversight

• ​Real-world examples and demos

​November 25, 2025
7:30 PM – 8:30 PM
Open to all developers building agentic systems