Skip to content

Chain-of-Thought (CoT)

A prompting technique where the model reasons step by step, improving accuracy on complex tasks.

Simply adding "Let's think step by step" often boosts math and logic accuracy. Modern "reasoning" models do this internally, so you may not need to prompt for it explicitly.

Related resources

Prompt Engineering Guide
A widely recognised, community-driven resource that systematically teaches prompt engineering — from foundational techniques like zero-shot and few-shot prompting to advanced methods such as chain-of-thought reasoning. It includes multilingual examples, model-agnostic design principles, and practical tips that help practitioners at every level improve AI output quality in a structured way.