LangGraph: Managing Agent Steps

This video shows how to modify an agent runtime to have more control over how the intermediate steps of an agent execution run are managed. This is useful for long running agents when there may be many steps.

Notebook (for chat agent runtime): https://github.com/langchain-ai/langgraph/blob/main/examples/chat_agent_executor_with_function_calling/managing-agent-steps.ipynb

Notebook (for agent executor, not covered in video but relevant): https://github.com/langchain-ai/langgraph/blob/main/examples/agent_executor/managing-agent-steps.ipynb