What is Chain-of-Thought (CoT)?
Last updated May 2026A prompting technique that asks AI to show its reasoning step by step.
Definition
Chain-of-Thought prompting is a technique where you instruct the AI to break down its reasoning into explicit, sequential steps before arriving at a final answer. This significantly improves accuracy on complex tasks like math, logic, coding, and analysis by forcing the model to "think through" the problem rather than jumping to a conclusion.
💡 Example
Instead of "What is 17 × 24?", use: "Calculate 17 × 24 step by step." The AI responds: "17 × 24 = 17 × 20 + 17 × 4 = 340 + 68 = 408." The step-by-step reasoning reduces errors.
Related concepts
The practice of crafting effective instructions to get better results from AI models.
Why this matters
Chain-of-thought prompting makes AI show its reasoning step by step, which dramatically improves accuracy on complex tasks. It is one of the most practical prompt engineering techniques — understanding it makes every AI tool you use more effective.
Real-world example
Instead of asking "What is 47 × 23?", you ask "Solve 47 × 23 step by step." The model breaks it into (47 × 20) + (47 × 3) = 940 + 141 = 1,081. This technique reduces errors on math, logic, coding, and analysis tasks by 20-40%.
See it in action
Providing a few examples in your prompt to teach the AI the pattern you want.
Explore AI tools
Find tools that use chain-of-thought (cot) in practice.
What is Chain-of-Thought (CoT)?
Chain-of-Thought prompting is a technique where you instruct the AI to break down its reasoning into explicit, sequential steps before arriving at a final answer. This significantly improves accuracy on complex tasks like math, logic, coding, and analysis by forcing the model to "think through" the problem rather than jumping to a conclusion.
How does Chain-of-Thought (CoT) work in practice?
Instead of "What is 17 × 24?", use: "Calculate 17 × 24 step by step." The AI responds: "17 × 24 = 17 × 20 + 17 × 4 = 340 + 68 = 408." The step-by-step reasoning reduces errors.
When should you use chain-of-thought prompting?
Chain-of-thought prompting is most effective for math problems, logic puzzles, multi-step reasoning, and complex analysis tasks. For simple factual questions or creative writing, it adds unnecessary overhead and may not improve results.
How do you trigger chain-of-thought reasoning in AI tools?
You can trigger it by adding phrases like "think step by step" or "show your reasoning" to your prompt. Some models like OpenAI's o1 and o3 have chain-of-thought built in and automatically reason through problems before answering.
What are the limitations of chain-of-thought prompting?
Chain-of-thought increases token usage and response time since the model generates more text. It can also produce convincing-sounding but incorrect reasoning steps, giving false confidence in wrong answers. Always verify the final conclusion independently.