AI Prompting Course

Master the Art of Prompt Engineering

Module 2Lesson 3
20 min

Chain-of-Thought (CoT) Prompting

Chain-of-Thought (CoT) prompting encourages an LLM to break down complex problems into intermediate reasoning steps. This mimics human step-by-step thinking and significantly improves reasoning abilities.

How It Works

Instead of just providing the final answer in examples, CoT includes the reasoning process:

Q: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?

A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11.

Q: A restaurant has 23 apples. They use 20 to make lunch and buy 6 more. How many apples does the restaurant have now?

A: ```

Advantages

  • Improved Reasoning: Significantly enhances complex reasoning
  • Transparency: Makes the reasoning process visible
  • Reduced Errors: Less likely to make simple mistakes

Limitations

  • Increased Complexity: Requires articulating reasoning clearly
  • Not Always Necessary: May be overkill for simple tasks

Exercise

Create a CoT prompt to solve a multi-step word problem. Show the reasoning steps explicitly.