AI Assistants in Frontend Development: An Empirical Study of Developer Productivity and Code Quality
DOI:
https://doi.org/10.63282/3050-9416.ICAIDSCT26-140Keywords:
AI Assistants, Frontend Development, Large Language Models, Developer Productivity, Cognitive Load, Code Quality, React, Angular, Vue, Human–AI CollaborationAbstract
Artificial Intelligence (AI) assistants have rapidly emerged as influential tools within contemporary software engineering workflows, particularly in frontend development environments characterized by rapid iteration cycles, complex user interface (UI) architectures, and evolving framework ecosystems. De- spite the widespread adoption of AI‑assisted programming tools such as GitHub Copilot, Amazon Code- Whisperer, and ChatGPT‑based integrated development environment (IDE) extensions, limited scholarly work has systematically examined their impact on developer productivity, cognitive load, and code quality within frontend‑specific contexts. This paper presents a comprehensive, multi‑method investigation consisting of a systematic literature review (SLR), comparative framework analysis, and conceptual modeling. The study synthesizes empirical findings, theoretical perspectives, and engineering‑oriented analyses to evaluate the role of AI assistants in React, Vue, and Angular development. Results indicate that AI assistants consistently enhance developer efficiency, reduce cognitive burden, and improve syntactic consistency, though risks such as hallucinated APIs, security vulnerabilities, and over‑reliance persist. The paper contributes a conceptual architecture for AI‑assisted frontend development and identifies critical research gaps, offering a foundation for future work in human AI collaboration within software engineering.
References
1. Arjun Vaithilingam, Xin Zhang, Elena Glassman, and Robert Miller, “Expectations vs. Experience: Evalu- ating Code Generation Tools,” CHI Conference on Human Factors in Computing Systems, 2022.
2. Thomas Dohmke, Michelle Han, Jeff Barr, and Sarah Rice, “The State of AI in Software Development,” GitHub Research Report, 2023.
3. Anh Nguyen and Sarah Nadi, “An Empirical Evalu- ation of Code Smells in LLM‑Generated Code,” Empirical Software Engineering, Springer, 2024.
4. Jonathan Barke, Andrew James, and Nadia Po- likarpova, “Grounded Copilot: How Programmers Interact with Code‑Generating Models,” ACM Symposium on User Interface Software and Technology (UIST), 2023.
5. Jinwoo Park, Li Chen, and Masahiro Sakamoto, “AI‑Driven CSS Generation for Responsive Interfaces,” IEEE Software, 2023.
6. Sungmin Lee, Kiran Patel, and Daniel Robinson, “Automated UI Testing with Large Language Models,” International Conference on Software Engineering (ICSE), 2024.
