Understanding Prompt Programming Tasks and Questions

TL;DR

This paper develops a taxonomy of prompt programming tasks and questions, revealing that current tools inadequately support developers' needs and many critical questions remain unanswered, highlighting opportunities for improved prompt programming tools.

Contribution

It introduces a comprehensive taxonomy of 25 tasks and 51 questions in prompt programming, and evaluates current tools' support for these aspects.

Findings

Prompt programming tasks are mostly done manually.

Many important questions asked by developers remain unanswered.

Current tools do not adequately support prompt programming needs.

Abstract

Prompting foundation models (FMs) like large language models (LLMs) have enabled new AI-powered software features (e.g., text summarization) that previously were only possible by fine-tuning FMs. Now, developers are embedding prompts in software, known as prompt programs. The process of prompt programming requires the developer to make many changes to their prompt. Yet, the questions developers ask to update their prompt is unknown, despite the answers to these questions affecting how developers plan their changes. With the growing number of research and commercial prompt programming tools, it is unclear whether prompt programmers' needs are being adequately addressed. We address these challenges by developing a taxonomy of 25 tasks prompt programmers do and 51 questions they ask, measuring the importance of each task and question. We interview 16 prompt programmers, observe 8 developers make prompt changes, and survey 50 developers. We then compare the taxonomy with 48 research and commercial tools. We find that prompt programming is not well-supported: all tasks are done manually, and 16 of the 51 questions -- including a majority of the most important ones -- remain unanswered. Based on this, we outline important opportunities for prompt programming tools.