Switching Perspectives in the Era of Artificial Intelligence-Assisted Software Development

The development of generative AI has changed the way software is developed by enabling code and system components to be generated through natural language instructions. Approaches such as AI-assisted software development and vibe coding have the potential to reduce the effort required to produce software, particularly for routine programming tasks and prototype development. However, the ease of producing code does not necessarily reduce the need for human judgment; on the contrary, as code becomes easier to produce, individuals involved in software development need to evaluate the results from multiple perspectives to ensure that the functionality, user experience, structure, security, and behavior of the system are considered holistically. This study proposes Perspective Switching as a conceptual lens for understanding how individuals attend to different aspects of a software system and explores its initial empirical manifestation through measures of perspective coverage and priority. A quantitative exploratory study was conducted using a short questionnaire containing Likert-scale items, behavioral checklists, and preference questions, distributed to 29 respondents who had experience developing, testing, using, or evaluating software systems. Findings show that respondents consistently considered more than one perspective, with an average coverage of 3.7 of the 6 analytical domains (functional, user, robustness/unexpected-use, system, maintainability, security/misuse) per respondent. The robustness/unexpected-use and system perspectives were considered most frequently, while the security/misuse and maintainability perspectives were considered least frequently. This study provides initial evidence of the existence and variation of Perspective Switching and discusses its importance in the context of AI-assisted software development, where the human role shifts from code production to critical evaluation and validation.

: Perspective Switching; AI-Assisted Software Development; Vibe Coding; Software Evaluation; Multi-Perspective Cognition

1. Brasoveanu, A., Moodie, M., & Agrawal, R. (2020). Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study. CEUR Workshop Proceedings, 2657, 1–9. https://doi.org/10.1145/nnnnnnn.nnnnnnn [Google Scholar] [Crossref]

2. Gupta, S., Epiphaniou, G., & Maple, C. (2023). AI-augmented usability evaluation framework for software requirements specification in cyber physical human systems. Internet of Things (Netherlands), 23. https://doi.org/10.1016/j.iot.2023.100841 [Google Scholar] [Crossref]

3. Gurunath Sakhalkar, P. (2025). AI-Assisted Code and Vulnerability Management: Transforming Modern Software Development. https://doi.org/10.32996/jcsts [Google Scholar] [Crossref]

4. Hu, X., Chen, Q., Wang, H., Xia, X., Lo, D., & Zimmermann, T. (2022). Correlating Automated and Human Evaluation of Code Documentation Generation Quality. ACM Transactions on Software Engineering and Methodology, 31(4). https://doi.org/10.1145/3502853 [Google Scholar] [Crossref]

5. Kauppinen, T. (2026). Generative Artificial Intelligence and Expert Work: Designing a Dynamic AI Capability. [Google Scholar] [Crossref]

6. Majdinasab, V., Bishop, M. J., Rasheed, S., Moradidakhel, A., Tahir, A., & Khomh, F. (2023). Assessing the Security of GitHub Copilot Generated Code -- A Targeted Replication Study. http://arxiv.org/abs/2311.11177 [Google Scholar] [Crossref]

7. Melo, A., Fagundes, R., Lenarduzzi, V., & Santos, W. B. (2022). Identification and measurement of Requirements Technical Debt in software development: A systematic literature review. Journal of Systems and Software, 194. https://doi.org/10.1016/j.jss.2022.111483 [Google Scholar] [Crossref]

8. Morgan, S., & Jamison, J. (2025). The Effect of Ai Code Generation on Developer Productivity I The Effect of Artificial Intelligence Code Generation on Software Developer Productivity. [Google Scholar] [Crossref]

9. Oruthotaarachchi, C. R., & Wijayanayake, W. M. J. I. (2025). Systematic Review of Software Product Value: Perspectives Beyond Functionality. In Information and Software Technology (Vol. 185). Elsevier B.V. https://doi.org/10.1016/j.infsof.2025.107784 [Google Scholar] [Crossref]

10. Perry, N., Srivastava, M., Kumar, D., & Boneh, D. (2023). Do Users Write More Insecure Code with AI Assistants? https://anonymous.4open. [Google Scholar] [Crossref]

11. Roberts, C., & Badi, S. (2026). Artificial Intelligence and Secure Coding Practices: A Comparative Analysis of AI-Assisted Development Platforms. [Google Scholar] [Crossref]

12. Rojas, A. M., Amaya, S. P., & Calderon, J. M. (2022). PBR Compiler: Automatic system description generator software. IFAC-PapersOnLine, 55(4), 219–224. https://doi.org/10.1016/j.ifacol.2022.06.036 [Google Scholar] [Crossref]

13. Shethiya, A. S. (2025). AI-Assisted Code Generation and Optimization in .NET Web Development. In Annals of Applied Sciences Annal. App. Sci (Vol. 6, Number 1). https://annalsofappliedsciences.com [Google Scholar] [Crossref]

14. Tuomimaa, J. (2025). Generative AI as a Source of Competitive Advantage in Decision-Making Processes: Dynamic Capability View. [Google Scholar] [Crossref]

15. Yilmaz, R., & Karaoglan Yilmaz, F. G. (2023). Augmented intelligence in programming learning: Examining student views on the use of ChatGPT for programming learning. Computers in Human Behavior: Artificial Humans, 1(2), 100005. https://doi.org/10.1016/j.chbah.2023.100005 [Google Scholar] [Crossref]

16. Yoo, S. H., & Kim, H. J. (2025). Security Analysis of Automated Code Generation: Structural Vulnerabilities in AI-Generated Code. Tehnicki Glasnik, 19(4), 560–574. https://doi.org/10.31803/tg-20250225095135 [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition