# Zero-Shot and Few-Shot Prompts

> The difference between zero-shot, one-shot and few-shot prompts. When a worked example helps, how to pick good ones, and what they cost.

**Course:** [Prompt Engineering](https://learn.benibix.com/learn/ai-working-with-ai)  
**Time:** 12 min

**After this lesson you can:**

- Tell zero-shot, one-shot and few-shot prompts apart
- Pick varied examples that show a pattern
- Say why examples do not train the model

## How many worked examples a prompt needs

A zero-shot prompt asks for a task with no worked examples. A one-shot prompt adds one, and a few-shot prompt adds a few, often two to five. Each example shows an input and the answer you want. A 2020 paper on GPT-3 showed a model could pick up a task from examples alone.

Start with zero-shot. Large models have seen so many tasks that a clear request is often enough. Is this review happy or unhappy needs no example. Zero-shot is the cheapest prompt, and it shows you what the model does on its own.

Add one example when the format comes out wrong. One worked answer shows the length, the layout and the tone better than a page of rules. The risk is that the model copies that one example too closely. It takes its words and quirks as well as its shape.

Add a few when one cannot show the whole pattern. Pick examples that differ from each other: a short input and a long one, an easy case and a hard one. Varied examples teach the pattern. Three that look alike teach the model to copy them.

Examples do not train the model. They only steer the request they sit in, and they cost tokens every time it is sent. Five long examples on a prompt sent 10,000 times a day add up to a real bill.

Wrap the examples in tags, so the model can tell them from the real task, and put the real task last. Check the answers in your examples with care. A model will copy a wrong answer in an example just as faithfully as a right one.

Newer models often need fewer examples than older ones. Many can follow a clear note on the format with none at all. So try the note first. Add examples only for what words cannot pin down, such as a tone, a style or a tricky case.

## Zero-shot, one-shot and few-shot side by side

| Prompt | Worked examples | Use it when |
| --- | --- | --- |
| Zero-shot | None | The task is common and the format is simple |
| One-shot | One | The format is easier to show than to describe |
| Few-shot | Two to five, most often | One example cannot show the whole pattern |

## Which one to pick

1. **Zero-shot.** Try it first on any common task. It is the cheapest, and it shows what the model does alone.
2. **One-shot.** Add one example when the answers are right but come back in the wrong shape.
3. **Few-shot.** Add a few mixed examples when one case cannot show the whole pattern.

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

### Example: Emma tags products in her shop

Emma asks for three tags for each product in her shop. Zero-shot, the tags come back in mixed styles, some long and some with capitals.

She adds two products with the tags she wants, inside example tags. All 40 of her test products then come back in her style.

**Words in this lesson:** [Zero-Shot Prompting](https://learn.benibix.com/term/ai/zero-shot-prompting), [One-Shot Prompting](https://learn.benibix.com/term/ai/one-shot-prompting), [Few-Shot Prompting](https://learn.benibix.com/term/ai/few-shot-prompting)

> **The one thing to remember.** Zero, one or a few is only the number of worked examples in the prompt. Examples steer one request. They never teach the model for good.

**Question:** What happens to a model after you give it a few-shot prompt?

**Answer:** Nothing lasts: the examples only steer that one request. Examples sit in the prompt and work only while they are there. The next request without them gets the model as it was.

---

Source: https://learn.benibix.com/learn/ai-working-with-ai/zero-shot-and-few-shot-prompts
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: 2026-11-20
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
