Back to guide/Education & Learning

Few-Shot Prompting (Learn by Example)

Few-shot prompting is showing the AI examples of what you want instead of explaining it. Two examples is usually enough for the AI to learn the pattern. This works for formatting, classification, tone matching — anything with a consistent pattern.

prompt-engineering-beginnersoutput_formatexample_input_1example_output_1
Edit View
Prompt
Convert the following items into {{output_format}}.

Here are examples of the format I want:

Input: {{example_input_1}}
Output: {{example_output_1}}

Input: {{example_input_2}}
Output: {{example_output_2}}

Now convert these:

Input: {{actual_input_1}}
Output:

Input: {{actual_input_2}}
Output:

Variables to customize

{{output_format}}{{example_input_1}}{{example_output_1}}{{example_input_2}}{{example_output_2}}{{actual_input_1}}{{actual_input_2}}

Why this prompt works

Few-shot prompting is showing the AI examples of what you want instead of explaining it. Two examples is usually enough for the AI to learn the pattern. This works for formatting, classification, tone matching — anything with a consistent pattern.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Sentiment Analysis

Requesting confidence and key phrases forces the model to justify its classification rather than guessing. The structured output format works zero-shot because sentiment analysis is well-understood by LLMs.

Key Information Extraction

Listing the exact fields to extract removes guesswork. The 'Not specified' instruction prevents hallucination when information is missing -- a common failure mode without this guardrail.

Question Answering with Source

Grounding the answer in source material and instructing the model to refuse when information is missing dramatically reduces hallucination -- the biggest risk in zero-shot Q&A.

Math Word Problem Reasoning

Explicit numbered steps force the model to decompose the problem rather than guessing. The verification step catches arithmetic errors before the final answer.