Chain-of-thought prompting

Chain-of-thought prompting is a technique that asks a language model to write out intermediate reasoning steps before its final answer, which often improves accuracy on math, logic and multi-step problems.

Chain-of-thought prompting sits in the Prompting & context part of the Agentik {OS} glossary, which defines the words used to build and run AI agent systems.

Also called chain of thought, CoT.