Few-shot prompting
Also called few-shot, multishot prompting, zero-shot
Showing an AI a few examples of what you want, so it copies the pattern instead of guessing it.
Describing a style in words is hard. Showing it is easy. Few-shot prompting means putting a handful of examples in your prompt (an input and the output you'd want for it) and then giving the real input. The model picks up the pattern: the length, the tone, the structure, even the quirks.
"Zero-shot" is the opposite: instructions only, no examples. That's fine for common tasks. Examples earn their place when the format is unusual, the tone is particular, or the model keeps getting it almost right.
The name comes from research on the early GPT models, which showed that a few examples in the prompt could teach a task without any retraining.
For example
Paste 3 product descriptions you like, then ask for a fourth in the same style for a new item.
Put it to use
Where you'll meet few-shot prompting in ChatGPT, Gemini and Claude, how to use it there, and the mix-up most people make.
Daily Bytes Plus is in the Android app.