What is Few-shot prompting?

Few-shot prompting is giving an AI model a handful of worked examples inside the prompt so it copies the pattern, format or style you want.

Instead of describing the output you want in the abstract, you show it — two or three input-and-output pairs that demonstrate the task. The model infers the rule from your examples and applies it to the new case. It's the fastest way to lock in a consistent format, tone or labelling scheme without any model training.

Few-shot shines when the task is easy to show but awkward to explain — a specific JSON shape, a house writing style, a tricky classification. With today's strongest models the examples often matter more for format alignment than for teaching the task itself, so two crisp, correct examples usually beat ten sloppy ones.