STREAMLINING SOFTWARE DEVELOPMENT: A COMPARATIVE STUDY OF AI-DRIVEN AUTOMATION TOOLS IN MODERN TECH
Keywords:
AI-Driven Automation, Software Development, Comparative Study, Artificial IntelligenceAbstract
The study examines a range of popular AI tools, focusing on their capabilities in code generation, testing, debugging, and project management. By analyzing the features, advantages, and limitations of these tools, the paper provides insights into their effectiveness and their role in shaping the future. Traditional methods of developing software are confronted with limitations in their correctness and efficiency, even if the size and complexity of software systems are constantly growing. New opportunities for automating tasks like testing, debugging, and project management have opened up thanks to artificial intelligence. These are only a few examples of the kind of tasks that may be mechanized with the help of AI, which would open up new avenues for automation. An automated system might also carry out testing and maintenance. With an eye towards improving productivity, decreasing the likelihood of human error, and speeding up the development process, this article will analyze the pros and cons of various technologies. An important takeaway from the study is the evidence that AI technologies are dramatically altering the software development process. These findings are derived on the research's thorough examination of the usability, scalability, and usefulness of such technologies. The findings show that AI has the ability to improve operational efficiency, but they also highlight the limitations due to implementation costs, a lack of learnt knowledge, and other factors. Software development projects will be more efficient and of higher quality if this study is successful in its long-term objective of providing developers and companies with a roadmap to AI automation solutions. Because of this, the study will be able to accomplish its final goal.
References
Sommerville, I. (2019). Engineering Software Products: An Introduction to Modern Software Engineering. Pearson.
Boehm, B. W. (1988). A spiral model of software development and enhancement. Computer, 21(5), 61–72.
Cheema, M. U., & Zearlish, Q. (n.d.). The choice of project management software by project managers; with the moderating impact of top management support. Journal of Management Research, 2(1).
Nascimento, E., Nguyen-Duc, A., Sundbø, I., & Conte, T. (n.d.). Software engineering for artificial intelligence and machine learning software: A systematic literature review.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (n.d.). Language models are unsupervised multitask learners.
Ahmad, A., Waseem, M., Liang, P., Fahmideh, M., Aktar, M. S., & Mikkonen, T. (2023). Towards human-bot collaborative software architecting with ChatGPT. Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering, Oulu, Finland: ACM, 279–285.
Katar, O., Özkan, D., Yildirim, Ö., & Acharya, U. R. (2023). Evaluation of GPT-3 AI language model in research paper writing. Turkish Journal of Science and Technology.
Akbar, M. A., Khan, A. A., & Liang, P. (2023). Ethical aspects of ChatGPT in software engineering research. arXiv, Jun. 13, 2023.
Fraiwan, M., & Khasawneh, N. (n.d.). A review of ChatGPT applications in education, marketing, software engineering, and healthcare: Benefits, drawbacks, and research directions.
Carter, R. A., Anton, A. I., Dagnino, A., & Williams, L. (2001). Evolving beyond requirements creep: A risk-based evolutionary prototyping model. Proceedings of the Fifth IEEE International Symposium on Requirements Engineering, 94–101.
Nelson, A. C., & Teng, J. T. C. (2000). Do systems development methodologies and CASE tools decrease stress among systems analysts? Behaviour & Information Technology, 19(4), 307–313.
Daugherty, P. R., & Wilson, H. J. (2018). Human + Machine: Reimagining Work in the Age of AI. Harvard Business Review Press.
