Prompting & context · Glossary term

What is Chain of Thought (CoT)?

Intermediate reasoning used to decompose a task before producing an answer. A prompt can request a visible rationale, while some systems use internal reasoning that is not returned to the user.

What people say

“Asking the model to show every step of its thinking.”

Why does Chain of Thought (CoT) matter?

Decomposition can help on multi-step tasks, but a fluent rationale is not proof that the answer is correct or that the text faithfully represents the model's internal computation.

Chain of Thought (CoT) in practice

Ask for a concise plan, independently check the result, and request verifiable calculations or citations instead of relying on a long reasoning transcript.

What is the common confusion about Chain of Thought (CoT)?

Chain of thought is not a substitute for tools, tests, or external verification.

Learn Chain of Thought (CoT) in the course

Start with

  • Few-Shot, Chain-of-Thought, Tree-of-Thought

    Telling a model what to do is prompting. Showing it how to think is engineering. The gap between 78% and 91% accuracy on the same model, same task, same data is not a better model.

    Phase 11: LLM Engineering

Taught in Phase 11: LLM Engineering.

  • Prompt EngineeringDesigning model-facing instructions, examples, constraints, and output requirements to improve behavior on a defined task.
  • Verification GateA control point that blocks progress until defined evidence satisfies a correctness or quality criterion.
  • Evaluation (Eval)A defined process for measuring model or system behavior on representative tasks using explicit success criteria, data, scorers, and…

More terms in Prompting & context

Open the Prompting & context list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.