NoCodeGPT: A No-Code Interface for Building Web Apps with Language Models

TL;DR

This paper introduces NoCodeGPT, a specialized interface that enables users with limited programming experience to build web applications using language models like GPT, improving usability and success rates.

Contribution

We designed and evaluated NoCodeGPT, a tool that enhances language model interactions for web app development by providing contextual prompts and version control features.

Findings

Majority of users successfully built web apps with NoCodeGPT

Compared to standard ChatGPT, success rates improved significantly

The tool facilitated easier and more effective web app creation for novices.

Abstract

In this paper, we first report an exploratory study where three participants were instructed to use ChatGPT to implement a simple Web-based application. A key finding of this study revealed that ChatGPT does not offer a user-friendly interface for building applications, even small web systems. For example, one participant with limited experience in software development was unable to complete any of the proposed user stories. Then, and as the primary contribution of this work, we decided to design, implement, and evaluate a tool that offers a customized interface for language models like GPT, specifically targeting the implementation of small web applications without writing code. This tool, called NoCodeGPT, instruments the prompts sent to the language model with useful contextual information (e.g., the files that need to be modified when the user identifies and requests a bug fix). It also saves the files generated by the language model in the correct directories. Additionally, a simple version control feature is offered, allowing users to quickly revert to a previous version of the code when the model enters a hallucination process, generating worthless results. To evaluate our tool, we invited 14 students with limited Web development experience to implement two small web applications using only prompts and NoCodeGPT. Overall, the results of this evaluation were quite satisfactory and significantly better than those of the initial study (the one using the standard ChatGPT interface). More than half of the participants (9 out of 14) successfully completed the proposed applications, while the others completed at least half of the proposed user stories.