Glossary · 3 · Working with models: prompts and context
Chain-of-thought prompting
Also known as: CoT, Step-by-step prompting
Chain-of-thought prompting asks a language model to work through a problem in explicit intermediate steps before giving its answer, which improves results on tasks that need reasoning, such as calculations, comparisons or multi-step checks.
- Intermediate
- Technical writers
- Technical project managers
- Developers
In one sentence
Chain-of-thought prompting: ask the model to reason step by step for better answers on complex tasks — and when reasoning models do it for you.
Example
“First list every product variant mentioned in the change request. Then check each variant against the topic list. Then report which topics need updates.”
Why it matters on your learning path
- Technical writers: Breaking a review task into explicit steps makes AI checks more thorough and easier to verify.
- Technical project managers: Step-by-step output makes AI decisions auditable — useful for reviews and sign-offs.
- Developers: Reasoning models do this internally; for them, explicit step instructions matter less.