Prompt Engineering Guide · Lesson 2

Zero-Shot and Few-Shot Prompting

When a single instruction is enough, and when examples are needed. How to write effective few-shot examples and why format consistency matters.

25 min read2 questions in quizReady prompt includedIn progress

Practical exercise

What to do after this lesson

Write a few-shot prompt for classifying customer support tickets into three categories (Return, Technical Support, General Question). Use 3 examples with a consistent format. Test on two new tickets.

Ready-to-use prompt

Template for this lesson

Copy and adapt to your context. Text in angle brackets should be replaced.

[TASK DESCRIPTION]

Example 1:
Input: [EXAMPLE_1]
Output: [ANSWER_1]

Example 2:
Input: [EXAMPLE_2]
Output: [ANSWER_2]

Example 3:
Input: [EXAMPLE_3]
Output: [ANSWER_3]

Input: [YOUR_DATA]
Output:

Common mistakes

What people get wrong

Inconsistent example format — the model gets confused about which pattern to follow.
Too few examples for complex tasks — one example doesn't establish a reliable pattern.
All examples from the same class — the model may ignore other categories.
Adding explanations inside examples — examples should be clean input/output pairs, no commentary.

Pro tips

What works but no one documents

Zero-Shot: No Examples Needed

A zero-shot prompt is a request with no demonstration examples. You describe the task and expect the model to handle it from its training.

Modern large language models (GPT-4, Claude, Gemini) perform well on zero-shot tasks thanks to the scale of their training.

Zero-shot classification example:

Classify the sentiment of the following review. Reply with one word: positive, negative, or neutral. Review: "Delivery arrived on time, the product matches the description, but the packaging was slightly dented."

For clearly defined tasks with an obvious format, zero-shot works great.

Few-Shot: Learning by Example

Few-shot prompting means showing the model several input → expected output pairs before your actual request. The model recognises the pattern and applies it.

Weak few-shot (inconsistent format):

Question: Capital of France? Answer: Paris is a beautiful city on the Seine. Q: Capital of Germany? A: Berlin Question: Capital of Japan?

Problem: format shifts (Question/Answer vs. Q/A), answer lengths vary. The model doesn't know which pattern to follow.

Strong few-shot (consistent format):

Classify the news article by topic. Topics: Sports, Technology, Politics, Culture. Article: "Apple unveiled a new M4 chip for the MacBook Pro." Topic: Technology Article: "Brazil's national team reached the World Cup final." Topic: Sports Article: "The government approved the new 2025 budget." Topic: Politics Article: "The film 'Dune' won three Academy Awards." Topic:

A single consistent pattern (Article / Topic) with three examples clearly establishes what to do.

When Few-Shot Is Essential

Few-shot particularly helps when:

The task requires a non-standard output format

A specific style or tone is needed

Classification uses custom categories

Data extraction must follow a precise structure

Example: extracting data in a specific format:

Extract the name, title, and company from the text. Format: JSON. Text: "Meeting with Anna Petrova, VP of Marketing at TechStart, went well." Result: {"name": "Anna Petrova", "title": "VP of Marketing", "company": "TechStart"} Text: "Ivan Sokolov, senior developer at DataFlow, presented a new product." Result: {"name": "Ivan Sokolov", "title": "senior developer", "company": "DataFlow"} Text: "Maria Ivanova, CEO of CloudBase, raised a $5M Series A." Result:

Report a bug

Zero-Shot and Few-Shot Prompting

Quiz — 2 questions

Zero-Shot: No Examples Needed

Few-Shot: Learning by Example

How Many Examples?

When Few-Shot Is Essential

Example Order Matters