Chain-of-Thought: Make the AI Show Its Work

Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reasoning problems. Here's why and when.

24 min · Reviewed 2026

The four magic words

Adding 'think step by step' or 'let's work through this carefully' to a prompt can flip an AI from wrong to right on math, logic, and planning problems. Researchers call this technique chain-of-thought, or CoT.

With and without CoT

WITHOUT CoT:
Q: A shirt costs $20 and is 25% off. Then you use a $5 coupon on the discounted price. What do you pay?
A: $10.  <-- often wrong

WITH CoT:
Q: A shirt costs $20 and is 25% off. Then you use a $5 coupon on the discounted price. What do you pay? Think step by step.
A: 
- Original price: $20.
- 25% of $20 is $5.
- Discounted price: $20 - $5 = $15.
- Apply $5 coupon: $15 - $5 = $10.
Final answer: $10.  <-- shows reasoning, more reliably correctCoT turns a guess into a verifiable chain.

Here the final number is the same, but with CoT you can check each step. If a step is wrong, you see it. Without CoT, the AI could give you '$15' and you wouldn't know why.

Phrasings that trigger CoT

'Think step by step.'
'Let's reason through this carefully.'
'Before giving your final answer, write out your reasoning.'
'Work it out one piece at a time.'
'Show your thinking as a numbered list, then give the answer.'

When to use CoT

Use CoT	Skip CoT
Multi-step math.	Quick factual lookup.
Logic puzzles.	Creative writing.
Planning and scheduling.	Short answers or summaries.
Comparing options.	Simple translations.
Anywhere getting it wrong would matter.	Anywhere speed matters more than accuracy.

You are a careful tutor. A student asks:
"I have 3 tests coming up. Math is worth 20%, Science is worth 35%, and History is worth 45% of my grade. If I scored 92, 78, and 85 respectively, what's my final grade?"

Before you give a final number:
1. Write out what each score contributes.
2. Show the math.
3. Only then give the total.

Format:
**Step 1:** ...
**Step 2:** ...
**Step 3:** ...
**Final grade:** ...Structured CoT — you can verify each step.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prompting-chain-of-thought-builders

What is the core idea behind "Chain-of-Thought: Make the AI Show Its Work"?
1. Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reasoning problems. Here's why and when.
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which term best describes a foundational idea in "Chain-of-Thought: Make the AI Show Its Work"?
1. step-by-step reasoning
2. chain-of-thought
3. Save the best tone variant as a template for next time.
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
A learner studying Chain-of-Thought: Make the AI Show Its Work would need to understand which concept?
1. chain-of-thought
2. Save the best tone variant as a template for next time.
3. step-by-step reasoning
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
Which of these correctly reflects a principle in Chain-of-Thought: Make the AI Show Its Work?
1. 'Let's reason through this carefully.'
2. 'Before giving your final answer, write out your reasoning.'
3. 'Work it out one piece at a time.'
4. 'Think step by step.'
Which of these does NOT belong in a discussion of Chain-of-Thought: Make the AI Show Its Work?
1. 'Think step by step.'
2. Save the best tone variant as a template for next time.
3. 'Before giving your final answer, write out your reasoning.'
4. 'Let's reason through this carefully.'
What is the key insight about "Why it works" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. When the AI rushes to an answer, it's pattern-matching shallowly.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What is the key insight about "CoT is not proof" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. A confident-sounding chain of reasoning can still be wrong. CoT helps you SEE the mistake — but you still have to check.
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What is the recommended tip about "Level up your prompts" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
4. Add context before your request — role, background, constraints. A prompt like "You are a chemistry teacher.
Which statement accurately describes an aspect of Chain-of-Thought: Make the AI Show Its Work?
1. Adding 'think step by step' or 'let's work through this carefully' to a prompt can flip an AI from wrong to right on math, logic, and planni…
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What does working with Chain-of-Thought: Make the AI Show Its Work typically involve?
1. Save the best tone variant as a template for next time.
2. Here the final number is the same, but with CoT you can check each step. If a step is wrong, you see it.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which best describes the scope of "Chain-of-Thought: Make the AI Show Its Work"?
1. It is unrelated to prompting workflows
2. It applies only to the opposite beginner tier
3. It focuses on Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reason
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
4. With and without CoT
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Phrasings that trigger CoT
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. When to use CoT
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which of the following is a concept covered in Chain-of-Thought: Make the AI Show Its Work?
1. step-by-step reasoning
2. Save the best tone variant as a template for next time.
3. chain-of-thought
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…

← Back to interactive lesson

Tendril · Builders · Prompting

Chain-of-Thought: Make the AI Show Its Work

Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reasoning problems. Here's why and when.

24 min · Reviewed 2026

The four magic words

With and without CoT

WITHOUT CoT:
Q: A shirt costs $20 and is 25% off. Then you use a $5 coupon on the discounted price. What do you pay?
A: $10.  <-- often wrong

WITH CoT:
Q: A shirt costs $20 and is 25% off. Then you use a $5 coupon on the discounted price. What do you pay? Think step by step.
A: 
- Original price: $20.
- 25% of $20 is $5.
- Discounted price: $20 - $5 = $15.
- Apply $5 coupon: $15 - $5 = $10.
Final answer: $10.  <-- shows reasoning, more reliably correctCoT turns a guess into a verifiable chain.

Here the final number is the same, but with CoT you can check each step. If a step is wrong, you see it. Without CoT, the AI could give you '$15' and you wouldn't know why.

Phrasings that trigger CoT

'Think step by step.'
'Let's reason through this carefully.'
'Before giving your final answer, write out your reasoning.'
'Work it out one piece at a time.'
'Show your thinking as a numbered list, then give the answer.'

When to use CoT

Use CoT	Skip CoT
Multi-step math.	Quick factual lookup.
Logic puzzles.	Creative writing.
Planning and scheduling.	Short answers or summaries.
Comparing options.	Simple translations.
Anywhere getting it wrong would matter.	Anywhere speed matters more than accuracy.

You are a careful tutor. A student asks:
"I have 3 tests coming up. Math is worth 20%, Science is worth 35%, and History is worth 45% of my grade. If I scored 92, 78, and 85 respectively, what's my final grade?"

Before you give a final number:
1. Write out what each score contributes.
2. Show the math.
3. Only then give the total.

Format:
**Step 1:** ...
**Step 2:** ...
**Step 3:** ...
**Final grade:** ...Structured CoT — you can verify each step.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-prompting-chain-of-thought-builders

What is the core idea behind "Chain-of-Thought: Make the AI Show Its Work"?
1. Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reasoning problems. Here's why and when.
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which term best describes a foundational idea in "Chain-of-Thought: Make the AI Show Its Work"?
1. step-by-step reasoning
2. chain-of-thought
3. Save the best tone variant as a template for next time.
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
A learner studying Chain-of-Thought: Make the AI Show Its Work would need to understand which concept?
1. chain-of-thought
2. Save the best tone variant as a template for next time.
3. step-by-step reasoning
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
Which of these correctly reflects a principle in Chain-of-Thought: Make the AI Show Its Work?
1. 'Let's reason through this carefully.'
2. 'Before giving your final answer, write out your reasoning.'
3. 'Work it out one piece at a time.'
4. 'Think step by step.'
Which of these does NOT belong in a discussion of Chain-of-Thought: Make the AI Show Its Work?
1. 'Think step by step.'
2. Save the best tone variant as a template for next time.
3. 'Before giving your final answer, write out your reasoning.'
4. 'Let's reason through this carefully.'
What is the key insight about "Why it works" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. When the AI rushes to an answer, it's pattern-matching shallowly.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What is the key insight about "CoT is not proof" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. A confident-sounding chain of reasoning can still be wrong. CoT helps you SEE the mistake — but you still have to check.
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What is the recommended tip about "Level up your prompts" in the context of Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
4. Add context before your request — role, background, constraints. A prompt like "You are a chemistry teacher.
Which statement accurately describes an aspect of Chain-of-Thought: Make the AI Show Its Work?
1. Adding 'think step by step' or 'let's work through this carefully' to a prompt can flip an AI from wrong to right on math, logic, and planni…
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
What does working with Chain-of-Thought: Make the AI Show Its Work typically involve?
1. Save the best tone variant as a template for next time.
2. Here the final number is the same, but with CoT you can check each step. If a step is wrong, you see it.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which best describes the scope of "Chain-of-Thought: Make the AI Show Its Work"?
1. It is unrelated to prompting workflows
2. It applies only to the opposite beginner tier
3. It focuses on Telling the AI to 'think step by step' before answering dramatically improves its accuracy on reason
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
3. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
4. With and without CoT
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Phrasings that trigger CoT
2. Save the best tone variant as a template for next time.
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which section heading best belongs in a lesson about Chain-of-Thought: Make the AI Show Its Work?
1. Save the best tone variant as a template for next time.
2. When to use CoT
3. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…
4. Add 'I don't know' as an explicit option when retrieved context doesn't answer t…
Which of the following is a concept covered in Chain-of-Thought: Make the AI Show Its Work?
1. step-by-step reasoning
2. Save the best tone variant as a template for next time.
3. chain-of-thought
4. Starting with 'You are a senior physics teacher' changes Claude's whole answer —…

← Back to interactive lesson