Web application for classifying and assisting in incident management using OpenAI LLMs
Abstract
The proposal for a web application to assist in the management of technical incidents in the field of information technology is established. The implementation was carried out with a 3-layer architecture, based on web technologies using React, Laravel, and a relational database. Large language models were implemented, applying instruction design techniques to analyze descriptions of technical incidents and automatically provide suggestions and classify priority, based on criteria for incidents generated in the present. The proposal was developed based on the SCRUM agile methodology and validated with real users, who evaluated the functionality and accuracy of the system. The tool achieved a 77.3% accuracy in proposing correct suggestions, excelling in categories such as software and networks. These results demonstrated the usefulness of the solution as support in the selection of solutions and in reducing cognitive effort during the initial stages of diagnosis. It is concluded that the use of LLMs in technical support represents an effective alternative for optimizing processes, as long as it is used as a complement to human experience.
Downloads
References
Benitez Pereira, Leonardo Santiago & Pizzio, Robinson & Bonho, Samir & Souza, Leonardo & Junior, Antonio. (2023). Machine Learning for Classification of IT Support Tickets. 210-213. 10.1109/CyMaEn57228.2023.10051041.
Brown, T. B. et al. "Language Models are Few-Shot Learners". NeurIPS 33 (2020).
D. X. Long, et al., "Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models," arXiv preprint arXiv:2411.00492, 2024. Disponible en: https://arxiv.org/abs/2411.00492
Do, L. X., et al. Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models. arXiv preprint arXiv:2411.00492, November 2024.
Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency. arXiv preprint arXiv:2505.02133v1, 2024.
Hao, Y., et al. Planning Anything with Rigor: General-purpose Zero-shot Planning with LLM-based Formalized Programming. MIT News, April 2025.
Huang, Y., et al. Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey. arXiv preprint arXiv:2311.12351, 2023.
L. S. Benitez Pereira, et al., "Machine Learning for Classification of IT Support Tickets," 2023 International Conference on Cyber Management and Engineering (CyMaEn), 2023. doi: 10.1109/CyMaEn57228.2023.10051041
Laravel Documentation. "Laravel - The PHP Framework For Web Artisans". https://laravel.com/docs (2025).
LLM Support for Real-Time Technical Assistance. ResearchGate, September 2024.
Oracle Corporation. "MySQL Reference Manual". https://dev.mysql.com/doc (2025).
Purple Griffon, "Incident Categorisation in ITSM," Purple Griffon Blog, 2024. [Online]. Available: https://purplegriffon.com/blog/incident-categorisation. [Accessed: Dec. 6, 2024].
R. Russo, "Multi-Agent LLM Frameworks: A New Paradigm in Problem Solving," Medium, 2 julio 2024. Disponible en: https://medium.com/bip-xtech/multi-agent-llm-frameworks-a-new-paradigm-in-problem-solving-c03abdae6433
React Documentation. "React – A JavaScript Library for Building User Interfaces". https://reactjs.org/docs (2025).
Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
Sahoo, P., et al. A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications. arXiv preprint arXiv:2402.07927, February 2024.
V. Scotti y M. J. Carman, "LLM Support for Real-Time Technical Assistance," Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024. doi: 10.1007/978-3-031-70371-3_26
Copyright (c) 2025 Innovation and Software
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors exclusively grant the right to publish their article to the Innovation and Software Journal, which may formally edit or modify the approved text to comply with their own editorial standards and with universal grammatical standards, prior to publication; Likewise, our journal may translate the approved manuscripts into as many languages as it deems necessary and disseminates them in several countries, always giving public recognition to the author or authors of the research.
