# One-Shot Prompting

> A prompt with one worked example in it. The model copies its shape.

**Field:** Artificial Intelligence  
**Category:** Working with AI  
**Also known as:** One-Shot, Single-Example Prompting

## Think of it like

It is like showing a friend one folded paper plane. Then they fold the next one.

## Definition

One-shot prompting means you put just one worked example in your prompt. The example shows an input and the answer you want for it. The model copies the shape, tone and length of that one answer. It sits between zero-shot, with none, and few-shot, with a few. One example is often enough to fix the format. It can also make the model copy that example too closely.

## Example

Jack wants product titles in one style. He shows one: "Red mug, 300 ml, $9". The model writes the next 20 titles the same way.

## Example code

```text
Turn notes into a title.
Notes: blue cup, holds 300 ml, costs $8
Title: Blue cup, 300 ml, $8

Notes: green bowl, holds 1 litre, costs $12
Title:
```

One input and its answer, then a new input for the model to finish.

## Why it matters

It is the cheapest way to lock in a format. One example costs far fewer tokens than five.

## Common mistake

Picking an odd example. The model copies its quirks, like its length or its words, into every answer.

## Three principles

- **One example.** An input and its answer.
- **Copies the shape.** Format, tone and length.
- **Choose it well.** Its quirks spread to every reply.

## Related terms

- [Zero-Shot Prompting](https://learn.benibix.com/term/ai/zero-shot-prompting)
- [Few-Shot Prompting](https://learn.benibix.com/term/ai/few-shot-prompting)
- [Prompt (AI)](https://learn.benibix.com/term/ai/prompt)
- [Prompt Template](https://learn.benibix.com/term/ai/prompt-template)
- [Prompt Engineering](https://learn.benibix.com/term/ai/prompt-engineering)

## Taught in

- [Zero-Shot and Few-Shot Prompts](https://learn.benibix.com/learn/ai-working-with-ai/zero-shot-and-few-shot-prompts): Prompt Engineering, 5/16

![Three prompts side by side. Zero-shot holds only the task. One-shot holds the task and one worked example. Few-shot holds the task and three worked examples. Each ends with the new input for the model to finish.](https://learn.benibix.com/diagrams/ai3-shots.svg)

---

Source: https://learn.benibix.com/term/ai/one-shot-prompting
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
