Chain of thought: definition

Chain of thought is prompting a model to work through a problem step by step before giving its answer, which improves accuracy on anything that needs reasoning.

Ask a model for just the answer to a multi-step problem and it often guesses. Ask it to show its working first, and the accuracy jumps, because generating the intermediate steps keeps it honest, much like a student showing their work.

In production we use it where reasoning matters and hide the working from the user, keeping only the final, checked answer. It costs more tokens, so it is applied where it earns its keep, not everywhere.

Related terms

Prompt engineering: Prompt engineering is the craft of writing the instructions, examples, and context you give a model so it produces reliable, correctly formatted output for a specific task.
Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.
Token: A token is the unit a language model reads and writes in, roughly a word-piece of a few characters, and model pricing and limits are counted in tokens rather than words.