Chain-of-Thought
Breaks down reasoning into explicit steps
intermediate
COGNITIVE
What Is This Pattern?
The Chain of Thought Pattern instructs the AI to show its reasoning process step-by-step before arriving at a conclusion. This dramatically improves accuracy on complex problems and makes the AI's logic transparent and verifiable.
How It Works
You ask the AI to "think step by step" or "show your reasoning". The AI then breaks down the problem, considers each part, and builds toward a solution incrementally.
When To Use This Pattern
- Complex problems requiring multi-step reasoning
- You need to verify the AI's logic
- Mathematical or logical problems
- Debugging or troubleshooting scenarios
Example
✅ After (Strong)
Let's think step by step...Best Practices
- Explicitly ask for step-by-step reasoning
- Number the steps if you want specific structure
- Use for complex decisions or calculations
- Combine with persona for expert-level reasoning
Common Mistakes to Avoid
- Using it for simple questions (overkill)
- Not providing enough context for reasoning
- Expecting perfect logic (AI can still make errors)
- Forgetting to validate the reasoning yourself