Prompting
Chain of Thought
A prompting technique where you ask the AI to "think step by step" before giving an answer — usually leading to better reasoning.
01 ——
In plain English
Chain of Thought (CoT) is a prompting and training technique that gets a model to write out its reasoning process step by step before answering, instead of jumping straight to the conclusion.
Example:
- Without CoT: "What's 17 × 24?" → "408" (often wrong)
- With CoT: "What's 17 × 24? Think step by step." → "17 × 24 = 17 × 20 + 17 × 4 = 340 + 68 = 408"
Why it works: Writing out the reasoning gives the model more "thinking space" — more tokens to work through the problem. It also surfaces errors so they can be checked.
In modern reasoning models (like OpenAI's o1, o3, or Claude's extended thinking) chain of thought is built in: the model thinks privately for many tokens before producing the final answer.
02 ——
Related terms
Prompt Engineering
The practice of crafting inputs to an AI model carefully to get better, more reliable outputs.
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
System Prompt
The high-level instructions given to an AI model at the start of a conversation that define its role, behaviour, and constraints.
Few-shot Learning
A prompting technique where you include a handful of examples in the prompt so the AI learns the pattern you want it to follow.
Back to glossaryLast reviewed May 2026