NoCodeGPT: A No‐Code Interface for Building Web Apps With Language Models

ABSTRACT Background Language models are increasingly used by software developers. However, it remains unclear whether their standard chat‐based interfaces are suitable for software development—especially for users with limited programming experience. Objective This work presents a tool, called NoCodeGPT, that provides a customized interface for language models aimed at enabling the implementation of small web applications without writing code. Methods We first conducted an exploratory study in which three participants used ChatGPT to implement a simple web‐based application. After that, we designed and implemented a customized GPT interface, called NoCodeGPT. To evaluate this new interface, we asked 14 students with limited web development experience to build two small web applications using only prompts. Results The exploratory study showed that general‐purpose chat interfaces like ChatGPT are not user‐friendly for application development. One participant, for instance, was unable to complete any proposed user stories. In contrast, results with NoCodeGPT were encouraging: 9 out of 14 participants completed all user stories, while the remaining five completed at least half. Conclusion The standard GPT interface is not well‐suited for novice web developers. In response, we proposed, designed, and implemented a new interface that offers a more accessible experience for building web applications with language models.

Authors

Institutions

Publication Details

Journal
Software Practice and Experience
Published
2025-05-08
DOI
https://doi.org/10.1002/spe.3432
Citations
4
Primary Topic
Mobile and Web Applications
Type
article
Field-Weighted Citation Impact
12.98

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

NoCodeGPT: A No‐Code Interface for Building Web Apps With Language Models

Guilherme Amaral Avelino, Samuel Silvestre, Marco Túlio Valente, Bruno Castelo Branco et al.
4 citations
Software Practice and Experience
Mobile and Web Applications
12.98
article

NoCodeGPT: A No‐Code Interface for Building Web Apps With Language Models

Guilherme Amaral Avelino, Samuel Silvestre, Marco Túlio Valente, Bruno Castelo Branco, Mauricio Monteiro
article en
4 citations

Abstract

ABSTRACT Background Language models are increasingly used by software developers. However, it remains unclear whether their standard chat‐based interfaces are suitable for software development—especially for users with limited programming experience. Objective This work presents a tool, called NoCodeGPT, that provides a customized interface for language models aimed at enabling the implementation of small web applications without writing code. Methods We first conducted an exploratory study in which three participants used ChatGPT to implement a simple web‐based application. After that, we designed and implemented a customized GPT interface, called NoCodeGPT. To evaluate this new interface, we asked 14 students with limited web development experience to build two small web applications using only prompts. Results The exploratory study showed that general‐purpose chat interfaces like ChatGPT are not user‐friendly for application development. One participant, for instance, was unable to complete any proposed user stories. In contrast, results with NoCodeGPT were encouraging: 9 out of 14 participants completed all user stories, while the remaining five completed at least half. Conclusion The standard GPT interface is not well‐suited for novice web developers. In response, we proposed, designed, and implemented a new interface that offers a more accessible experience for building web applications with language models.

Software Practice and ExperienceVol. 55(8)
Instituto Federal de Educação, Ciência e Tecnologia de Minas Gerais (BR), Universidade Federal do Piauí (BR)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação de Amparo à Pesquisa do Estado de Minas Gerais
Openalex Percentile: Top 2%
Mobile and Web Applications
12.98
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.