Skip to main content
ModelTerms

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.

Few-ShotPrompting

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.

ReActAgents & Tools

ReAct is a prompting pattern that interleaves reasoning ("Thought:") with actions ("Action:") and observations ("Observation:"). It is the foundation of most tool-using agents.

PromptPrompting

A prompt is the text you send to an LLM to elicit a response. It typically includes a system message, optional examples, and the user's query.

Prompt EngineeringPrompting

Prompt engineering is the craft of writing prompts that reliably produce the behavior you want from an LLM. It blends formatting, examples, tone, and constraints.

Reasoning ModelArchitecture

A reasoning model spends extra compute thinking step-by-step before answering. OpenAI o1/o3, DeepSeek R1, and Anthropic's extended thinking are reasoning models.

Test-Time ComputePrompting

Test-time compute is the extra reasoning, sampling, or search a model can do at inference time to improve quality — more thinking tokens, more candidate answers, or verifier-guided search.

Self-ConsistencyPrompting

Self-consistency samples N chain-of-thought completions for the same problem and takes the majority answer. Improves accuracy on math and reasoning tasks at N× the cost.

Tree of ThoughtsPrompting

Tree of Thoughts generalizes chain-of-thought to a search tree: at each step the model produces multiple candidate thoughts, evaluates them, and explores the most promising branches — like beam search over reasoning.

Side-by-side comparisons

Sources