A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

By Jules White et al

Published on Feb. 21, 2023

Read the original document by opening this link in a new tab.

Table of Contents

Abstract
I. Introduction
II. Comparing Software Patterns with Prompt Patterns
III. A Catalog of Prompt Patterns for Conversational LLMs

Summary

This paper describes a catalog of prompt engineering techniques presented in pattern form that have been applied to solve common problems when conversing with large language models (LLMs) like ChatGPT. Prompt patterns are knowledge transfer methods providing reusable solutions for structuring prompts to customize outputs and interactions with LLMs. The paper introduces prompt patterns, compares them to software patterns, and presents a catalog of prompt patterns applied to automate software development tasks. The prompt patterns are categorized into Input Semantics, Output Customization, Error Identification, Prompt Improvement, and Interaction, each addressing specific aspects of using prompts with LLMs.