Enhancing Enterprise Data Engineering Workflows with AI-Powered Code Assistants: A Case Study on GitHub Copilot
Article Sidebar
Main Article Content
Abstract
The case study explores setting up GitHub Copilot, an AI code suggestion tool, in companies that develop and test enterprise data systems to boost their work efficiency. Through the review of literature published until 2020, the study discovers that software developer’s face some issues, including repeating certain actions, inefficient projects and a lack of smart-thinking environments. The study shows that GitHub Copilot helps meet software development challenges by offering real-time, suitable code suggestions for each task in the Software Development Lifecycle (SDLC). The discussion demonstrates that using the tool can lead to more automated work, fewer errors and quicker tests. At the end of the study, there are suggestions for further research, involving evaluating outcomes, adjusting for each area and considering social aspects of using AI in businesses.
Article Details
References
Beller, M., Gousios, G., Panichella, A., Proksch, S., Amann, S. and Zaidman, A., 2017. Developer testing in the ide: Patterns, beliefs, and behavior. IEEE Transactions on Software Engineering, 45(3), pp.261-284.
Bellman, C., Seet, A. and Baysal, O., 2018, May. Studying developer build issues and debugger usage via timeline analysis in visual studio IDE. In Proceedings of the 15th International Conference on Mining Software Repositories (pp. 106-109).
Bettini, L. and Crescenzi, P., 2015, July. Java-meets eclipse: An IDE for teaching Java following the object- later approach. In 2015 10th International Joint Conference on Software Technologies (ICSOFT) (Vol. 2, pp. 1-12). IEEE.
Businge, J., 2013. Co-evolution of the Eclipse framework and its third-party plug-ins.
Draxler, S., 2015. The appropriation of a software ecosystem: a practice take on the usage, maintenance and modification of the eclipse IDE.
Harishchandra Patel, “Impedance Control in HDI and Substrate-Like PCBs for AI Hardware Applications” (2024). Journal of Electrical Systems, 20(11s), 5109-5115.
Ioannou, C., Burattin, A. and Weber, B., 2018. Mining developers’ workflows from IDE usage. In Advanced Information Systems Engineering Workshops: CAiSE 2018 International Workshops, Tallinn, Estonia, June 11-15, 2018, Proceedings 30 (pp. 167-179). Springer International Publishing.
Jagadish, H.V., Gehrke, J., Labrinidis, A., Papakonstantinou, Y., Patel, J.M., Ramakrishnan, R. and Shahabi, C., 2014. Big data and its technical challenges. Communications of the ACM, 57(7), pp.86-94.
Kevic, K., Walters, B.M., Shaffer, T.R., Sharif, B., Shepherd, D.C. and Fritz, T., 2015, August. Tracing software developers' eyes and interactions for change tasks. In Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering (pp. 202-213).
Penumala, M.R. and Gonzalez-Sanchez, J., 2018. Towards embedding a tutoring companion in the eclipse integrated development environment. In Intelligent Tutoring Systems: 14th International Conference, ITS 2018, Montreal, QC, Canada, June 11–15, 2018, Proceedings 14 (pp. 352-358). Springer International Publishing.
Qiu, D., Li, B. and Leung, H., 2016. Understanding the API usage in Java. Information and software technology, 73, pp.81-100.
Raychev, V., Vechev, M. and Yahav, E., 2014, June. Code completion with statistical language models. In Proceedings of the 35th ACM SIGPLAN conference on programming language design and implementation (pp. 419-428).
Wang, Y., 2017, November. Characterizing developer behavior in cloud based IDEs. In 2017 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) (pp. 48-57). IEEE.