Chain-of-Thought
Also known as: CoT, Chain-of-Thought Prompting, Step-by-Step Reasoning
In one sentence
A prompting technique that asks AI to show its reasoning step-by-step, improving accuracy on complex tasks like maths, logic, and multi-step problem-solving.
Explain like I'm 12
When your teacher says 'show your working' on a maths test, you get better marks because you think through each step instead of jumping to the answer. Chain-of-thought does the same thing for AI — asking it to think step-by-step makes it get the right answer more often.
In context
Chain-of-thought prompting was introduced by Google researchers in 2022 and quickly became one of the most widely used prompting techniques. In its simplest form, adding 'Let's think step by step' to a prompt can improve accuracy on reasoning tasks. More advanced versions include few-shot CoT (providing worked examples), self-consistency (generating multiple reasoning paths and picking the most common answer), and tree-of-thought (exploring branching solution paths). In 2025, dedicated reasoning models like OpenAI's o1 and o3 build chain-of-thought into their architecture, generating internal reasoning before answering.
See also
Related Guides
Learn more about Chain-of-Thought in these guides:
Advanced Prompt Optimization
AdvancedSystematically optimize prompts: automated testing, genetic algorithms, prompt compression, and performance tuning.
7 min readPrompting 201: Structured Prompts & JSON Output
IntermediateAdvanced prompting: structured formats, JSON output, few-shot learning, chain-of-thought, and prompt templates for production.
11 min readPrompt Engineering Patterns: Proven Techniques
IntermediateMaster advanced prompting techniques: chain-of-thought, few-shot, role prompting, and more. Get better AI outputs with proven patterns.
8 min read