Prompting techniques
Zero-shot prompting
Definition
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.
Zero-shot is the default way most people use AI: describe what you want and let the model figure out the format. For summarisation, translation, general question answering and straightforward rewriting, it usually works fine.
It becomes unreliable when your task has an unusual output shape, a specific house style, or edge cases where "reasonable" answers differ. The model has to guess your conventions, and it will guess based on what is most common in training data rather than what you actually want.
The signal to switch to few-shot is inconsistency: if running the same prompt on ten inputs gives you eight formats, examples will fix it faster than more instructions.
Example
Zero-shot: "Classify this review as positive, negative or neutral: 'It works fine, nothing special.'"
Related terms
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.
Prompt
A prompt is the input you give an AI model to produce an output. Effective prompts specify five things: the role the model should adopt, relevant context, the specific task, the output format, and any constraints.
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.
Tree-of-thought
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.
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.
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.