Prompting techniques
Tree-of-thought
Definition
Tree-of-thought extends chain-of-thought by exploring several reasoning branches in parallel, evaluating each, and pursuing the most promising. It helps on problems where the first plausible path is often wrong.
Where chain-of-thought follows one line of reasoning, tree-of-thought generates multiple candidate next steps at each stage, scores them, and expands the best. It is closer to deliberate search than to intuition.
In practice this is implemented as an orchestration pattern rather than a single prompt: generate N approaches, evaluate each against criteria, select, then repeat. That makes it considerably more expensive than chain-of-thought — often several times the token cost.
Reserve it for problems where a wrong early commitment is costly and verification is cheap: planning, puzzles with dead ends, and design decisions with several viable directions.
Related terms
Chain-of-thought prompting
Chain-of-thought prompting asks a model to work through its reasoning step by step before answering. It measurably improves accuracy on maths, logic, and multi-step problems by forcing intermediate steps instead of an immediate guess.
Self-consistency
Self-consistency runs the same reasoning prompt several times at non-zero temperature and takes the most common answer. It trades cost for accuracy on problems with a single verifiable result.
AI agent
An AI agent is a system where a model plans and takes actions through tools in a loop, rather than producing a single response. It decides what to do next, does it, observes the result, and continues until the goal is met.
Zero-shot prompting
Zero-shot prompting means asking a model to do a task with no worked examples — just an instruction. It works well for common tasks the model has seen extensively in training.
Few-shot prompting
Few-shot prompting means including two to five worked examples of the input-output pattern you want before making your real request. It is the fastest way to lock in a consistent format, tone or edge-case behaviour.
Meta-prompting
Meta-prompting is using a model to write, critique or improve prompts. You describe the task and the failure modes you want to avoid, and the model drafts the prompt.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.