Evaluating AI Agentic Workflows in Full-Stack Development: A Case Study on Vue.js and NestJS

Ricco Herdiyan Saputra; Dita Novita Sari

Authors

Ricco Herdiyan Saputra Institut Bakti Nusantara Author
Dita Novita Sari Institut Bakti Nusantara Author

Keywords:

AI agentic workflows, Full-stack development, Vue.js, NestJS, Software automation

Abstract

The current evolution of software technology demands full-stack architectures that are increasingly modular and efficient, yet the complexity of integrating backend and frontend layers frequently triggers inefficiencies within the software development life cycle. Current literature leaves a gap regarding the quantitative evaluation of end-to-end full-stack integration orchestration using AI agentic workflows. This study aimed to evaluate the performance, generative code accuracy, and time efficiency of applying AI agentic workflows in modern full-stack application development. We adopted an experimental research design, utilizing intelligent coding platforms as autonomous agents to orchestrate the generation of a codebase bridging a Vue.js frontend with a NestJS and Prisma backend. The research systematically recorded development time, generative accuracy through a defined Code Acceptance Rate, and structural maintainability via cyclomatic complexity. The experimental results revealed a substantial 70.7% reduction in total development time, decreasing from 48.5 hours via manual baseline methods to just 14.2 hours using the AI-assisted workflows. Furthermore, the autonomous agents achieved a high Code Acceptance Rate of 89.4%, reduced average integration error rates to 4.5%, and generated more maintainable code structures with lower cyclomatic complexity. Agents excelled at standardized boilerplate but encountered context loss on complex business logic. This study concludes that orchestrating autonomous agents within the software engineering life cycle significantly optimizes development efficiency and functions as powerful cross-platform synchronization tools. Future research must prioritize enhanced context-preservation algorithms and structured Human-in-the-Loop governance protocols.

References

[1] Y. N. Nugroho, D. S. Kusumo, and M. J. Alibasa, “Clean architecture implementation impacts on maintainability aspect for backend system code base,” presented at the 2022 10th International Conference on Information and Communication Technology (ICoICT), IEEE, 2022, pp. 134–139.

[2] N. Weber, “Evaluation and comparison of full-stack JavaScript technologies,” 2022.

[3] P. Linjanja, Scalable Application Development with NestJS: Leverage REST, GraphQL, microservices, testing, and deployment for seamless growth. Packt Publishing Ltd, 2025.

[4] M. K. R. Jaggavarapu, “The evolution of agentic AI: architecture and workflows for autonomous systems,” Journal Of Multidisciplinary, vol. 5, no. 7, pp. 418–427, 2025.

[5] N. Krishnan, “Ai agents: Evolution, architecture, and real-world applications,” arXiv preprint arXiv:2503.12687, 2025.

[6] R. Sapkota, K. I. Roumeliotis, and M. Karkee, “Vibe coding vs. agentic coding: Fundamentals and practical implications of agentic ai,” arXiv preprint arXiv:2505.19443, 2025.

[7] F. Khan, “Agentic AI applications in software development: a systematic mapping study,” 2026.

[8] M. M. Hasan, H. Li, E. Fallahzadeh, G. K. Rajbahadur, B. Adams, and A. E. Hassan, “An empirical study of testing practices in open source AI agent frameworks and agentic applications,” Empirical Software Engineering, vol. 31, no. 5, p. 124, 2026.

[9] I. Kolawole, A. M. Osilaja, and V. E. Essien, “Leveraging artificial intelligence for automated testing and quality assurance in software development lifecycles,” International Journal of Research Publication and Reviews, vol. 5, no. 12, pp. 4386–4401, 2024.

[10] R. H. Saputra, L. Asiyani, and D. Novitasari, “DEVELOPMENT OF MOBILE WEB APPLICATIONS TO IMPROVE ACCESS TO INFORMATION AND SERVICES (CASE STUDY: PEKON TANJUNG REJO),” Asia Information System Journal, vol. 4, no. 2, 2025.

[11] R. H. Saputra, D. Novitasari, and W. Waziana, “Penerapan Webgis Dalam Mendukung Aksesibilitas Informasi Pasar Tradisional Di Wilayah Lampung Tengah,” POSITIF: Jurnal Sistem dan Teknologi Informasi, vol. 12, no. 1, 2026.

[12] M. Kamal and T. A. Bablu, “Mobile applications empowering smallholder farmers: A review of the impact on agricultural development,” International Journal of Social Analytics, vol. 8, pp. 36–50, 2023.

[13] L. N. Amali, M. S. Tuloli, and M. R. Katili, “Digital Transformation for Rural Empowerment: A Web-Based Application Framework to Enhance BUMDesa Performance,” Jambura Journal of Informatics, vol. 8, no. 1, pp. 27–39, 2026.

[14] A. Aiswarya et al., “Community empowerment through geospatial data collection. Presenting the empower app: a secure, scalable and configurable mobile platform,” presented at the 2023 IEEE 11th Region 10 Humanitarian Technology Conference (R10-HTC), IEEE, 2023, pp. 1100–1105.

[15] R. H. Saputra and D. Novitasari, “Analisis Efisiensi Struktur Data pada Implementasi SISKEUDES: Studi Kasus Pekon Gunung Kasih,” Simpatik: Jurnal Sistem Informasi Dan Informatika, vol. 5, no. 2, pp. 123–131, 2025.

[16] R. H. Saputra and W. Waziana, “EVALUATION OF THE USABILITY AND USER EXPERIENCE (UX) OF THE EDLINK PLATFORM IN SUPPORTING DISTANCE LEARNING AT THE BAKTI NUSANTARA INSTITUTE,” Asia Information System Journal, vol. 5, no. 01, pp. 01–11, 2026.

[17] K. S. Adewole et al., “Expert system and decision support system for electrocardiogram interpretation and diagnosis: review, challenges and research directions,” Applied Sciences, vol. 12, no. 23, p. 12342, 2022.

[18] H. Banjar, S. Almalki, L. Almehmadi, A. Alshahrani, A. Chaudhary, and R. Ghoname, “Knowledge‐Based Expert System for Orthopedic Injury Management With Integrated Transcutaneous Electrical Nerve Simulation Therapy,” International Journal of Telemedicine and Applications, vol. 2025, no. 1, p. 5878245, 2025.

[19] M. el-Khaeri Kesuma and R. H. Saputra, “Design Thinking UI/UX: Teori dan Praktik,” Penerbit Mifandi Mandiri Digital, vol. 1, no. 01, 2024.

[20] F. Satria and R. H. Saputra, “Analysis of student perceptions of the use of artificial intelligence in learning in the digital age,” RADEN INTAN: Proceedings on Family and Humanity, vol. 2, no. 1, pp. 299–308, 2025.

[21] W. Waziana, W. Andewi, R. H. Saputra, M. Muslihudin, and I. B. Oktarin, “ChatGPT use patterns and higher-order thinking performance in EFL argumentative writing,” Language Education & Assessment, vol. 9, pp. 104947–104947, 2026.

[22] I. A. P. A. Sinthiya and R. H. Saputra, “Generative AI, Deepfake, dan Hak Cipta di Indonesia dalam Tinjauan Yuridis,” Asas Wa Tandhim: Jurnal Hukum, Pendidikan Dan Sosial Keagamaan, vol. 6, no. 1, pp. 27–38, 2027.

[23] J. Liu, C. S. Xia, Y. Wang, and L. Zhang, “Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation,” Advances in neural information processing systems, vol. 36, pp. 21558–21572, 2023.

[24] H. Cui, M. Xie, T. Su, C. Zhang, and S. H. Tan, “An empirical study of false negatives and positives of static code analyzers from the perspective of historical issues,” arXiv preprint arXiv:2408.13855, 2024.

[25] R. Tufano, O. Dabić, A. Mastropaolo, M. Ciniselli, and G. Bavota, “Code review automation: strengths and weaknesses of the state of the art,” IEEE Transactions on Software Engineering, vol. 50, no. 2, pp. 338–353, 2024.

[26] L. Pokorny, “Characterizing AI-enabled social engineering threats to US national security: A mixed-methods analysis for developing defensive policy and technical countermeasures,” 2026.

[27] J. Sivakumar, N. R. Salman, F. R. Salman, H. R. Salimova, and E. Ghimire, “AI-driven cyber threat detection: enhancing security through intelligent engineering systems,” Journal of Information Systems Engineering and Management, vol. 10, no. 19, pp. 790–798, 2025.

[28] A. Mohsin, H. Janicke, A. Ibrahim, M. I. Sarker, and S. Camtepe, “A unified framework for human–ai collaboration in security operations centers with trusted autonomy,” ACM Transactions on Internet Technology, 2025.