Chain of Thought (CoT) prompting asks the AI to show its reasoning step by step before giving a final answer — dramatically improving accuracy on hard tasks.

How to Trigger It

• "Think step by step"
• "Let's work through this carefully"
• "First, reason through the problem, then give your answer"
• "Show your work"

When to Use It

• Math and logic problems
• Legal and medical reasoning
• Multi-step coding tasks
• Any complex decision

Reference:

Chain of thought prompting

https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/chain-of-thought