An Intelligent Resume Builder based on Modern Web Architecture using Generative Artificial Intelligence
Article Sidebar
Main Article Content
Abstract
This research aims to develop and evaluate an intelligent resume generation system capable of adapting content to specific job requirements by integrating artificial intelligence with a serverless edge computing architecture. The system was developed using Next.js, Tailwind CSS, Hono Framework on Cloudflare Workers, and Cloudflare D1, together with the Gemini 2.5 Flash API for automated resume content analysis, recommendation, and summarization. The results indicate that the proposed system successfully supports the complete resume creation process, including information input, template selection, AI-assisted processing, and PDF export. The system also demonstrated fast response performance through the Cloudflare Edge Network. Overall performance evaluation was at a high level ( = 3.94, S.D. = 1.00) The highest-rated item was the appropriateness of colors, web tone, and font sizes (
= 4.38, S.D. = 0.83), followed by the rapid response of the web application (
= 4.22, S.D. = 0.94), and the accurate real-time resume preview (
= 4.19, S.D. = 1.00). The findings demonstrate that the developed system can significantly enhance resume creation efficiency and highlight the potential of integrating artificial intelligence with modern web applications for future intelligent system development.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles in this journal are copyrighted by the x may be read and used for academic purposes, such as teaching, research, or citation, with proper credit given to the author and the journal.use or modification of the articles is prohibited without permission.
statements expressed in the articles are solely the opinions of the authors.
authors are fully responsible for the content and accuracy of their articles.
other reuse or republication requires permission from the journal."
References
ชูศรี วงศ์รัตนะ. (2564). เทคนิคการใช้สถิติเพื่อการวิจัย (พิมพ์ครั้งที่ 15). กรุงเทพฯ : ศูนย์หนังสือจุฬาลงกรณ์ มหาวิทยาลัย.
สถาบันวิจัยเพื่อการพัฒนาประเทศไทย. (2561). ปรับทิศทางเศรษฐกิจไทยให้พร้อมสู่ยุคแห่งความปั่นป่วน
ทางเทคโนโลยี (TDRI Report ฉบับที่ 142). เข้าถึงได้จาก : https://tdri.or.th/wp-content/ uploads/2018/09/wb142.pdf (สืบค้นเมื่อ : 9 พฤศจิกายน 2568).
สำนักงานสถิติแห่งชาติ. (2569). สรุปผลการสำรวจภาวะการทำงานของประชากร ไตรมาสที่ 4 พ.ศ. 2568. กระทรวงดิจิทัลเพื่อเศรษฐกิจและสังคม. เข้าถึงได้จาก : https://www.nso.go.th/nsoweb/storage/ survey_detail/2026/20260223141532_13518.pdf (สืบค้นเมื่อ : 9 มีนาคม 2569).
Anil, R., Borgeaud, S., Wu, Y., Cai, J.-F., Firat, O., Zhong, L., ... & Gemini Team. (2024). Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Cloudflare. (2024). Cloudflare Workers and D1. Available at: https://developers.cloudflare.com (Accessed: 9 December 2025).
Flanagan, D. (2020). JavaScript: The Definitive Guide: Master the World's Most-Used Programming Language. O’Reilly Media.
Gan, C., Zhang, Q., & Mori, T. (2024). Application of LLM agents in recruitment: A novel framework for resume screening. arXiv preprint arXiv:2401.08315.
Google. (2024). Gemini API. Available at: https://ai.google.dev (Accessed: 12 October 2025).
Hipp, R. (2024). SQLite. Available at: https://www.sqlite.org (Accessed: 30 October 2025).
Hono contributors. (2024). Hono. Available at: https://hono.dev (Accessed: 8 December 2025).
Jadhav, P., Deshmukh, A., & Kulkarni, S. (2025). CLEVERCV: Gen-AI Driven Resume Builder Enhancing Resume Creation and ATS Optimization. International Journal of Creative Research Thoughts (IJCRT), 13(1), 458–467.
Jonas, E., Schleier-Smith, J., Sreekanti, V., Tsai, C.-C., Khandelwal, A., Pu, Q., & Patterson, D. A. (2019). Cloud programming simplified: A Berkeley view on serverless computing. arXiv preprint arXiv:1902.03383.
Mardan, A. (2017). React and React Native. Apress.
Min, B., Ross, H., Sulem, E., Veyseh, A. P. B., Nguyen, T. H., Sainz, O., & Roth, D. (2023). Recent advances in natural language processing via large pre-trained language models: A survey. ACM Computing Surveys, 56(2), 1–40.
Mungi, N. V. S. R. (2022). Resume Screening Using Machine Learning. Journal of Engineering Sciences, 13(09), 23–28.
Norman, D. (2013). The Design of Everyday Things: Revised and Expanded Edition. Basic Books.
Riva, M. (2022). Real-World Next.js: Build Scalable, High-Performance, and Modern Web Applications Using Next.js. Packt Publishing.
Tailwind Labs. (2024). Tailwind CSS. Available at: https://tailwindcss.com (Accessed: 5 February 2026).
Tayal, S., Sharma, T., Singhal, S., & Thakur, A. (2024). Resume Screening using Machine Learning. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(2), 182–189.
Torvalds, L., & Git contributors. (2024). Git. Available at: https://git-scm.com/ (Accessed: 24 March 2026).
Vercel. (2024). Next.js Documentation. Available at: https://nextjs.org/docs (Accessed: 15 January 2026).
Yelubolu, S. C., Vinay, T., Mahesh, D. Y. S. R., Lukeshbabu, P., Surya, D. N. V. S., & Krishna, O. S. R. (2026). Automated ATS-Optimized Resume Builder with Dynamic Templates. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 14(3), 115–124.
