Prompting · beginner
Chain-of-Thought (CoT)
Chain-of-thought prompting asks the model to show its reasoning step by step before giving a final answer. It dramatically improves performance on multi-step problems.
Explanation
Adding "Let's think step by step" or showing examples that include reasoning before the answer pushes the model to externalize intermediate steps. For math, logic, and multi-hop reasoning, this often turns failure into success — the model can use earlier reasoning steps as context for later ones.
Modern frontier models (GPT-4-class, Claude Sonnet+, o1/o3) increasingly do this implicitly: their post-training already produces step-by-step responses without you asking. The "reasoning models" of 2025 take this further with internal scratchpads that get hidden from the final output.
Examples
- "Solve this word problem step by step." — model shows working.
- o1 / o3 / DeepSeek-R1 reasoning before user-visible answer.
Frequently asked
What is Chain-of-Thought?
Chain-of-thought prompting asks the model to show its reasoning step by step before giving a final answer. It dramatically improves performance on multi-step problems.
What is an example of chain-of-thought?
"Solve this word problem step by step." — model shows working.
How is Chain-of-Thought related to Few-Shot?
Chain-of-Thought and Few-Shot are both prompting concepts. Few-shot prompting includes a small number of input-output examples directly in the prompt so the model can pattern-match without any fine-tuning.
Is Chain-of-Thought considered beginner?
Chain-of-Thought is generally considered beginner-level material in the AI and LLM space.