# A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

**Authors:** Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, Douglas C. Schmidt  
**arXiv:** [2302.11382](https://arxiv.org/abs/2302.11382)  
**Date:** 2023-02-21  
**Summary page:** https://www.summarizepaper.com/en/paper/2302.11382v1/

## Key points

- The paper presents a catalog of prompt engineering techniques for effective communication with large language models (LLMs) like ChatGPT.
- Prompts are instructions given to LLMs to enforce rules, automate processes, and ensure specific qualities and quantities of generated output.
- Prompt patterns are reusable solutions to common problems faced in output generation and interaction when working with LLMs.
- The authors provide a framework for documenting patterns for structuring prompts that can be adapted to different domains.
- A catalog of patterns that have been successfully applied to improve the outputs of LLM conversations is presented.
- Prompts can be built from multiple patterns, and some benefit from combination with other prompt patterns.
- Developing prompt engineering skills is essential for effective communication with LLMs like ChatGPT and automating software development tasks.
- This paper provides valuable insights into using prompts as a form of programming that can customize the outputs and interactions with an LLM.

## Summary

The paper titled "A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT" presents a comprehensive catalog of prompt engineering techniques that can be used to converse effectively with large language models (LLMs) such as ChatGPT. Prompts are instructions given to an LLM to enforce rules, automate processes, and ensure specific qualities and quantities of generated output. The paper describes prompt patterns as a knowledge transfer method analogous to software patterns since they provide reusable solutions to common problems faced in a particular context, i.e., output generation and interaction when working with LLMs. The authors provide a framework for documenting patterns for structuring prompts that can solve a range of problems so that they can be adapted to different domains. They also present a catalog of patterns that have been applied successfully to improve the outputs of LLM conversations. The paper explains how prompts can be built from multiple patterns and illustrates prompt patterns that benefit from combination with other prompt patterns. The contributions of this research on prompt engineering apply LLMs to automate software development tasks and emphasize the importance of developing prompt engineering skills for effective communication with LLMs like ChatGPT. This paper provides valuable insights into the use of prompts as a form of programming that can customize the outputs and interactions with an LLM. It is an essential resource for researchers, developers, and practitioners who work with large language models and want to enhance their conversational abilities by using prompts effectively.