Accelerating Low Code Automation Development with Generative Artificial Intelligence

Abstract

This thesis investigates the integration of Generative Artificial Intelligence (Generative AI) into low code automation development platforms, with a particular emphasis on enhancing Robotic Process Automation (RPA). This study centers on three crucial points: the influence of Generative AI on the functionality of low code automation tools, the challenges and limitations of using Generative AI within these platforms, and the strategies to mitigate such challenges. Through a comprehensive literature review and a case study approach involving semi-structured interviews with RPA experts and citizen developers, this research addresses critical questions concerning the efficiency, challenges, mitigations, and future prospects of incorporating Generative AI into low code automation development efforts. The research findings highlight that while Generative AI offers considerable advantages in terms of functionality enhancement and accessibility, it also poses significant challenges such as issues with accuracy, reliability, and a steep learning curve for effective utilization. The study proposes strategic mitigation efforts, including improved training and algorithmic adjustments, user education and interaction design, continuous learning and adaption and enhanced contextual understanding, to address these challenges. This research contributes insights into the integration of Generative AI in low code automation development platforms, suggesting a promising yet challenging path forward in leveraging these technologies to foster more inclusive, efficient, and accessible development practices.