Chain-of-Thought Prompting
Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.
Goal
Reduce rushed-inference errors by surfacing intermediate reasoning steps instead of jumping straight to the answer.
Steps
-
1
Identify a question requiring multi-step reasoning (calculation, comparison, planning, multi-factor decision).
Expected Outcome
Evidence base
School: Prompt Engineering / Reasoning Research
Founders: Jason Wei (Google Research) · Anthropic Research Team (2022)
The paper "Chain-of-Thought Prompting Elicits Reasoning" (Wei et al., Google 2022) proved that surfacing intermediate steps raises reasoning-task accuracy by dozens of percentage points versus direct questioning.
Keywords
Frequently asked questions
How long does "Chain-of-Thought Prompting" take?
When will I notice the effect of "Chain-of-Thought Prompting"?
Is "Chain-of-Thought Prompting" evidence-based?
Is "Chain-of-Thought Prompting" suitable for beginners?
Subscribe for full access
Subscribe to Plus for full access to this practice and the whole catalogue, or try first — free, no sign-in, no commitment.
7 complete practices (one per domain) are free forever, no sign-in.