Skip to content
Back to full roadmap
topiccore

Chain-of-Thought (CoT)

Writing 'think step by step' boosts math/logic accuracy by 20-60%.

3 hours3 resources1 prereqs

CoT makes the model write out intermediate reasoning — focusing attention on those steps.

3 variants:

  1. Zero-shot CoT — "Think step by step, then give your answer"
  2. Few-shot CoT — show example question-with-reasoning pairs
  3. Auto-CoT — model generates its own examples

New 'reasoning' models (o1, Claude thinking, Gemini 2.5) internalize CoT automatically. But on older/smaller models, it's still critical.

Prerequisites

Resources(3)

Chain-of-Thought (CoT) · Prompt Engineer Roadmap | Şükrü Yusuf Kaya