AI Codex
Agents & OrchestrationDevelopers

Chain-of-Thought Prompting

Also: CoT

A technique where you ask Claude to 'think step by step' before giving its final answer — rather than jumping straight to a conclusion. This dramatically improves accuracy on complex problems like math, logic, or multi-step reasoning. When Claude shows its work, you also get to see where its reasoning might be flawed. The practical version: adding "think through this step by step" to your prompt often significantly improves the quality of the response.

In practice

You ask Claude a math problem and it gets it wrong. You add "think through this step by step" to your prompt and it walks through the calculation out loud — and gets it right. That's chain-of-thought prompting. Making Claude show its work often dramatically improves accuracy on anything that requires multiple reasoning steps.

Related concepts