What is Chain-of-Thought Prompting?
Asking an AI to show its reasoning step by step before giving a final answer, which often improves accuracy on complex tasks.
Chain-of-Thought Prompting explained in plain English
Analogy
Chain-of-thought prompting is like requiring a student to show their working on a maths paper rather than writing only the final number. The steps reveal — and often correct — mistakes along the way.
Example
A user solving a multi-step word problem gets a better result by prompting: "Think through this step by step, then give the final answer."
How is Chain-of-Thought Prompting used?
Developers use chain-of-thought prompting to improve maths, logic, and reasoning in LLMs. Asking "explain your steps" before the answer is a simple version anyone can use in ChatGPT.
Common misconceptions about Chain-of-Thought Prompting
Showing steps does not guarantee correctness — models can confabulate convincing but wrong reasoning chains.
People also read
- Inference
The phase when a trained model is actually used — taking new input and producing a prediction or response.
- Prompt
The input text or instruction given to an AI model to guide its response.
- RAG
A technique that combines AI language models with external knowledge retrieval for more accurate answers.
- AI slop
A colloquial term referring to the low-quality or unhelpful output generated by artificial intelligence systems
- average precision at k
A measure of the accuracy of a model's top k predictions
- black box model
A type of machine learning model that is complex and difficult to interpret or understand
- Confabulation
When an AI produces a confident, fluent answer that sounds true but is factually wrong — generating plausible language without a reliable link to reality.
- Context Window
The maximum amount of text a language model can consider at one time, measured in tokens.
- conversational coding
A method of programming where users can create software by having a conversation with a computer
- deterministic
A system or process that always produces the same output given the same inputs