Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Few-shot prompting

Few-shot prompting is giving a language model a handful of worked examples of a task inside the prompt, so it can copy the pattern for a new input without any retraining.

Also called: in-context learning, few-shot, multishot prompting

By Divya Sharma · Checked Nov 15, 2026 · How we review

In a few-shot prompt, you show the model several input and output pairs, then give it a new input and let it complete the pattern. The model's weights do not change. It picks up the task from the examples in its context, which is why the ability is also called in-context learning.

Where the term comes from

The idea was popularised by the GPT-3 paper, "Language Models are Few-Shot Learners". The authors applied GPT-3 to many tasks with no gradient updates or fine-tuning, specifying each task and its demonstrations purely as text in the prompt. They reported that scaling up the model greatly improved this few-shot performance.

Example

To classify support tickets, a prompt might list three tickets, each followed by its label (billing, bug, account), then a fourth ticket with no label. The model is expected to answer with one of the same labels in the same format.

Why it matters

Examples are often a clearer way to show format and tone than a long description. Anthropic's prompting guide calls them one of the most reliable ways to steer output format, tone and structure. They are a standard part of prompt engineering.

How it differs from zero-shot

A zero-shot prompt gives only an instruction with no examples. One-shot gives a single example. Few-shot gives several.

Limits

Each example costs input tokens on every call. The model may copy surface details of the examples, such as length or wording, so examples should vary. Few-shot prompting also cannot teach the model facts it lacks; for that, consider retrieval-augmented generation or fine-tuning.

Related terms

Zero-shot
Zero-shot means asking a model to do a task from an instruction alone, with no worked examples in the prompt and no task-specific training. The model relies only on what it already learned.
Prompt engineering
Prompt engineering is the practice of writing, structuring and testing the instructions and examples given to a language model so that it produces the output an application needs, without changing the model's weights.
Chain-of-thought
Chain-of-thought (CoT) is a prompting method in which a language model writes out intermediate reasoning steps before its final answer, which tends to improve results on maths, logic and other multi-step problems.
Fine-tuning
Fine-tuning is further training of a pretrained model on a smaller, task-specific dataset, so the model adopts a particular skill, format, tone or domain without being trained from scratch.
System prompt
A system prompt is the block of instructions an application sends to a language model before the user's messages. It sets the model's role, rules, tone and output format for the whole conversation.

Sources