CoPrompt: Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming

TL;DR

This paper introduces CoPrompt, a tool designed to facilitate prompt sharing and referencing among programmers using natural language programming with large language models, aiming to improve collaboration and reduce communication overhead.

Contribution

The paper presents a formative study on collaborative NL programming challenges and introduces CoPrompt, a prototype supporting prompt sharing, referring, and linking to enhance teamwork.

Findings

CoPrompt helps programmers understand collaborators' prompts more effectively.

It reduces repetitive updates and communication costs.

User study shows improved collaboration efficiency.

Abstract

Natural language (NL) programming has become more approachable due to the powerful code-generation capability of large language models (LLMs). This shift to using NL to program enhances collaborative programming by reducing communication barriers and context-switching among programmers from varying backgrounds. However, programmers may face challenges during prompt engineering in a collaborative setting as they need to actively keep aware of their collaborators' progress and intents. In this paper, we aim to investigate ways to assist programmers' prompt engineering in a collaborative context. We first conducted a formative study to understand the workflows and challenges of programmers when using NL for collaborative programming. Based on our findings, we implemented a prototype, CoPrompt, to support collaborative prompt engineering by providing referring, requesting, sharing, and linking mechanisms. Our user study indicates that CoPrompt assists programmers in comprehending collaborators' prompts and building on their collaborators' work, reducing repetitive updates and communication costs.