<overview A decision model answers typed questions about state and returns probabilities instead of prose. It replaces the common pattern of prompting an LLM, parsing its text, and branching on the result. - — binary question, returns a probability of yes - — picks one label, returns the full distribution plus confidence - — grades against an ordered rubric, returns an expected value plus confidence is a LangChain , so it drops into a node like any other runnable. Up to 32 questions share one request and are answered independently — your code combines them. Reach for one when a node generates…