Chain-of-Thought (CoT)

Chain-of-thought prompting asks the model to reason step by step before giving an answer. It is useful for multi-step reasoning, calculations, and transparent decision workflows.

Intermediate Reasoning enhancement

When to use

Use it for math, logic, multi-step classification, and decisions where the reasoning path should be inspectable.

Task: Apply Chain-of-Thought (CoT) to the user's request.

Context: describe the input, constraints, target audience, and desired format.

Instruction: be explicit, keep the output structured, and state any assumptions.

Structured answer based on the requested technique.

Key result: the model follows the stated task and format.
Notes: validate the output before using it in production.

Best practices

• Ask for concise step-by-step reasoning.
• Combine with few-shot examples for harder tasks.
• Define the required reasoning structure.
• Ask for a final answer after the reasoning.

Common pitfalls

• It adds cost and latency for simple tasks.
• Long reasoning chains can introduce intermediate errors.
• A plausible explanation can still be wrong.