PromptForge
AI Glossary

Prompting techniques

Zero-shot prompting

Also known as: zero shot

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

Put this into practice

Understanding the term is step one. Our free courses and tools let you actually use it.