Notes by Lex Toumbourou

Chain-of-Thought Prompting is a [[Few-Shot Prompting]] technique where model is given examples of step-by-step reasoning rather than standard question and answer examples, encouraging the model to think through a problem before returning an answer.

Part of the Planning category of Agentic Reasoning design patterns.

Described in paper Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.