Abstract

The following thesis explores the integration of Artificial Intelligence (AI) technologies into the discipline of Software Engineering (SWE) on the case study of the development of the open-source project Experimental Hub. Experimental Hub is an online experimentation platform developed for psychologists and other scientists, and represents a relevant contribution to the digitization and enhancement of efficiency of scientific research processes. In particular, in this work we attempt to quantify the impact of using AI tools, especially OpenAI’s Chat Generative Pre-trained Transformer (ChatGPT) as the most wellknown and widely used Large Language Model (LLM), on various aspects of the software development workflow. Our analysis involves investigating the project’s initial state and the exploration of possible improvement areas to enhance user experience and functionality, distinguishing between the workflows of three user types: experimenters, participants, and developers. We then describe the coding and debugging measures taken to implement these improvements and the criteria used when ordering them chronologically in our project timeline. Finally, we analyze the effect of using ChatGPT as a pair-programmer in various development stages, evaluating the tool’s performance for different use cases. Our analysis gives an insight into the benefits and drawbacks of integrating AI-based tools into the software industry, with the aim to provide more clarity about this ever more relevant topic and stimulate other researchers to further investigate in this field of research

Results/Implementation/Project Description

Conclusion

[ PDF (optional) ] 

[ Slides Kickoff/Final (optional)]