The Software Industrial Revolution: Engineering Implications of AI Generated Software
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V7I1P143Keywords:
AI Generated Software, Software Engineering, Generative AI, Software Architecture, Automated Development, AI Assisted CodingAbstract
Generative artificial intelligence systems capable of producing functional software from natural language instructions are rapidly transforming software engineering workflows. Modern AI development tools can generate application programming interfaces, infrastructure configurations, databases, and deployment pipelines within minutes. While much of the public discussion focuses on productivity improvements, the deeper engineering implications of these tools remain underexamined. This paper analyzes how AI assisted code generation changes the structure of software engineering practice. We argue that the role of developers shifts from direct implementation toward architectural reasoning, requirement definition, and system verification. The paper examines AI assisted development workflows, architectural implications, testing challenges, and long term maintainability risks associated with AI generated software. Finally, we propose a future development lifecycle where humans focus on problem definition while AI systems perform implementation, testing, deployment, and monitoring tasks.
Downloads
References
[1] T. B. Brown et al., “Language Models Are Few-Shot Learners,” NeurIPS, 2020.
[2] S. Nijkamp et al., “CodeGen: An Open Large Language Model for Code Generation,” 2022.
[3] J. Chen et al., “Evaluating Large Language Models Trained on Code,” 2021.
[4] M. Fowler, Refactoring: Improving the Design of Existing Code, Addison-Wesley, 2018.
[5] D. Parnas, “On the Criteria To Be Used in Decomposing Systems into Modules,” CACM, 1972.
[6] Gangani, C. M., Sakariya, A. B., Bhavandla, L. K., & Gadhiya, Y. (2024). Blockchain and AI for secure and compliant cloud systems. Webology, 21(3).
