Perceptions of the use of AI code generation tools ("vibe coding") and low-code platforms regarding technical debt and software architecture among advanced students in university software development programs in Cúcuta, 2026
Published
:Issue
:Section
:License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Downloads
Generative Artificial Intelligence, Low-Code, Software Architecture, Technical Debt, Vibe Coding
The accelerated growth of generative artificial intelligence tools applied to software development and the expansion of low-code platforms have transformed programming, documentation, and software construction dynamics in both academic and professional environments. This article aims to characterize the perception of advanced university students related to software development programs in Cúcuta regarding the use of AI-based code generation tools (vibe coding) and low-code platforms, as well as their relationship with technical debt and software architecture decisions during 2026. The research adopts a mixed-method approach with a descriptive scope and a non-experimental cross-sectional design. Data collection includes structured surveys, semi-structured interviews, and documentary review of authorized technical evidence. The study expects to identify the most frequently used tools, perceived benefits in productivity and learning, and risks associated with maintainability, code comprehension, technological dependency, component integration, and architectural sustainability. The findings will support the formulation of guidelines for the responsible adoption of generative AI and low-code tools in university environments related to software engineering.
Alamin, M. A. A., Uddin, G., Malakar, S., Afroz, S., Haider, T., & Iqbal, A. (2023). Developer discussion topics on the adoption and barriers of low code software development platforms. Empirical Software Engineering, 28, Article 4. https://doi.org/10.1007/s10664-022-10244-0
Alfonso, I., Conrardy, A., Sulejmani, A., Nirumand, A., Ul Haq, F., Gomez-Vazquez, M., Sottet, J.-S., & Cabot, J. (2024). Building BESSER: An open-source low-code platform. In H. van der Aa, D. Bork, R. Schmidt, & A. Sturm (Eds.), Enterprise, business-process and information systems modeling: BPMDS and EMMSAD 2024 (Lecture Notes in Business Information Processing, Vol. 511, pp. 203–212). Springer. https://doi.org/10.1007/978-3-031-61007-3_16
Butler, J., Suh, J., Haniyur, S., & Hadley, C. (2025). Dear diary: A randomized controlled trial of generative AI coding tools in the workplace. In 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) (pp. 319–329). IEEE. https://doi.org/10.1109/ICSE-SEIP66354.2025.00034
Cruz Trochez, A. C., Bastidas Díaz, B. A., & Pardo Calvache, C. J. (2026). La gestión de la deuda de procesos en equipos de desarrollo de software: Una revisión sistemática de la literatura. Prospectiva, 24(1), 1–14. https://doi.org/10.15665/rp.v24i1.3741
Departamento Nacional de Planeación. (2025). Política nacional de inteligencia artificial (Documento CONPES 4144). https://colaboracion.dnp.gov.co/CDT/Conpes/Econ%C3%B3micos/4144.pdf
Estevez Gonzalez, J. C. (2024). Prototipo de aplicación móvil utilizando una herramienta de desarrollo multiplataforma para trabajadores de servicios independientes [Trabajo de grado de pregrado, Universidad Autónoma de Bucaramanga]. Repositorio Institucional UNAB. http://hdl.handle.net/20.500.12749/22618
Käss, S., Strahringer, S., & Westner, M. (2022). Drivers and inhibitors of low code development platform adoption. In 2022 IEEE 24th Conference on Business Informatics (CBI) (pp. 196–205). IEEE. https://doi.org/10.1109/CBI54897.2022.00028
Martínez Ramírez, A. F., & Cruz Fajardo, J. C. (2019). Prototipo de software mediante plataformas low-code para automatizar el proceso de recepción y emisión de facturación electrónica: Caso de estudio Redsis S.A.S. [Trabajo de grado de especialización, Universidad Distrital Francisco José de Caldas]. Repositorio Institucional de la Universidad Distrital Francisco José de Caldas. http://hdl.handle.net/11349/22864
Meske, C., Hermanns, T., von der Weiden, E., Loser, K.-U., & Berger, T. (2025). Vibe coding as a reconfiguration of intent mediation in software development: Definition, implications, and research agenda. IEEE Access, 13, 213242–213259. https://doi.org/10.1109/ACCESS.2025.3645466
Pérez, B. R. (2023). Deuda técnica en arquitectura: Una estrategia de identificación. Ingeniería y Competitividad, 25(3), e-21413071. https://doi.org/10.25100/iyc.v25i3.13071
Pérez-Gutiérrez, B. R., Castellanos, C., & Correal, D. (2020). A computational model of a natural language processing system for architectural technical debt management. Journal of Physics: Conference Series, 1587(1), Article 012020. https://doi.org/10.1088/1742-6596/1587/1/012020
Pérez-Gutiérrez, B. R., Correal, D. E., & Vera-Rivera, F. H. (2022). Un enfoque de machine learning para apoyar la identificación de la deuda técnica en arquitectura. Mundo FESC, 12(23), 126–140. https://doi.org/10.61799/2216-0388.1198
Pinto, G., de Souza, C., Rocha, T., Steinmacher, I., de Souza, A., & Monteiro, E. (2024). Developer experiences with a contextualized AI coding assistant: Usability, expectations, and outcomes. In Proceedings of the 2024 IEEE/ACM 3rd International Conference on AI Engineering—Software Engineering for AI (CAIN ’24) (pp. 81–91). Association for Computing Machinery. https://doi.org/10.1145/3644815.3644949
Ray, P. P. (2025). A review on vibe coding: Fundamentals, state-of-the-art, challenges and future directions [Preprint]. TechRxiv. https://doi.org/10.36227/techrxiv.174681482.27435614/v1
Rios, N., de Mendonça Neto, M. G., & Spínola, R. O. (2018). A tertiary study on technical debt: Types, management strategies, research trends, and base information for practitioners. Information and Software Technology, 102, 117–145. https://doi.org/10.1016/j.infsof.2018.05.010
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022). Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In Extended abstracts of the 2022 CHI Conference on Human Factors in Computing Systems (pp. 1–7). Association for Computing Machinery. https://doi.org/10.1145/3491101.3519665
The accelerated growth of generative artificial intelligence tools applied to software development and the expansion of low-code platforms have transformed programming, documentation, and software construction dynamics in both academic and professional environments. This article aims to characterize the perception of advanced university students related to software development programs in Cúcuta regarding the use of AI-based code generation tools (vibe coding) and low-code platforms, as well as their relationship with technical debt and software architecture decisions during 2026. The research adopts a mixed-method approach with a descriptive scope and a non-experimental cross-sectional design. Data collection includes structured surveys, semi-structured interviews, and documentary review of authorized technical evidence. The study expects to identify the most frequently used tools, perceived benefits in productivity and learning, and risks associated with maintainability, code comprehension, technological dependency, component integration, and architectural sustainability. The findings will support the formulation of guidelines for the responsible adoption of generative AI and low-code tools in university environments related to software engineering.
Alamin, M. A. A., Uddin, G., Malakar, S., Afroz, S., Haider, T., & Iqbal, A. (2023). Developer discussion topics on the adoption and barriers of low code software development platforms. Empirical Software Engineering, 28, Article 4. https://doi.org/10.1007/s10664-022-10244-0
Alfonso, I., Conrardy, A., Sulejmani, A., Nirumand, A., Ul Haq, F., Gomez-Vazquez, M., Sottet, J.-S., & Cabot, J. (2024). Building BESSER: An open-source low-code platform. In H. van der Aa, D. Bork, R. Schmidt, & A. Sturm (Eds.), Enterprise, business-process and information systems modeling: BPMDS and EMMSAD 2024 (Lecture Notes in Business Information Processing, Vol. 511, pp. 203–212). Springer. https://doi.org/10.1007/978-3-031-61007-3_16
Butler, J., Suh, J., Haniyur, S., & Hadley, C. (2025). Dear diary: A randomized controlled trial of generative AI coding tools in the workplace. In 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) (pp. 319–329). IEEE. https://doi.org/10.1109/ICSE-SEIP66354.2025.00034
Cruz Trochez, A. C., Bastidas Díaz, B. A., & Pardo Calvache, C. J. (2026). La gestión de la deuda de procesos en equipos de desarrollo de software: Una revisión sistemática de la literatura. Prospectiva, 24(1), 1–14. https://doi.org/10.15665/rp.v24i1.3741
Departamento Nacional de Planeación. (2025). Política nacional de inteligencia artificial (Documento CONPES 4144). https://colaboracion.dnp.gov.co/CDT/Conpes/Econ%C3%B3micos/4144.pdf
Estevez Gonzalez, J. C. (2024). Prototipo de aplicación móvil utilizando una herramienta de desarrollo multiplataforma para trabajadores de servicios independientes [Trabajo de grado de pregrado, Universidad Autónoma de Bucaramanga]. Repositorio Institucional UNAB. http://hdl.handle.net/20.500.12749/22618
Käss, S., Strahringer, S., & Westner, M. (2022). Drivers and inhibitors of low code development platform adoption. In 2022 IEEE 24th Conference on Business Informatics (CBI) (pp. 196–205). IEEE. https://doi.org/10.1109/CBI54897.2022.00028
Martínez Ramírez, A. F., & Cruz Fajardo, J. C. (2019). Prototipo de software mediante plataformas low-code para automatizar el proceso de recepción y emisión de facturación electrónica: Caso de estudio Redsis S.A.S. [Trabajo de grado de especialización, Universidad Distrital Francisco José de Caldas]. Repositorio Institucional de la Universidad Distrital Francisco José de Caldas. http://hdl.handle.net/11349/22864
Meske, C., Hermanns, T., von der Weiden, E., Loser, K.-U., & Berger, T. (2025). Vibe coding as a reconfiguration of intent mediation in software development: Definition, implications, and research agenda. IEEE Access, 13, 213242–213259. https://doi.org/10.1109/ACCESS.2025.3645466
Pérez, B. R. (2023). Deuda técnica en arquitectura: Una estrategia de identificación. Ingeniería y Competitividad, 25(3), e-21413071. https://doi.org/10.25100/iyc.v25i3.13071
Pérez-Gutiérrez, B. R., Castellanos, C., & Correal, D. (2020). A computational model of a natural language processing system for architectural technical debt management. Journal of Physics: Conference Series, 1587(1), Article 012020. https://doi.org/10.1088/1742-6596/1587/1/012020
Pérez-Gutiérrez, B. R., Correal, D. E., & Vera-Rivera, F. H. (2022). Un enfoque de machine learning para apoyar la identificación de la deuda técnica en arquitectura. Mundo FESC, 12(23), 126–140. https://doi.org/10.61799/2216-0388.1198
Pinto, G., de Souza, C., Rocha, T., Steinmacher, I., de Souza, A., & Monteiro, E. (2024). Developer experiences with a contextualized AI coding assistant: Usability, expectations, and outcomes. In Proceedings of the 2024 IEEE/ACM 3rd International Conference on AI Engineering—Software Engineering for AI (CAIN ’24) (pp. 81–91). Association for Computing Machinery. https://doi.org/10.1145/3644815.3644949
Ray, P. P. (2025). A review on vibe coding: Fundamentals, state-of-the-art, challenges and future directions [Preprint]. TechRxiv. https://doi.org/10.36227/techrxiv.174681482.27435614/v1
Rios, N., de Mendonça Neto, M. G., & Spínola, R. O. (2018). A tertiary study on technical debt: Types, management strategies, research trends, and base information for practitioners. Information and Software Technology, 102, 117–145. https://doi.org/10.1016/j.infsof.2018.05.010
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022). Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In Extended abstracts of the 2022 CHI Conference on Human Factors in Computing Systems (pp. 1–7). Association for Computing Machinery. https://doi.org/10.1145/3491101.3519665