Design Principles for Collaborative Generative AI Systems in Software Development

Generative artificial intelligence (GAI) has the potential to transform software development practices with prior research indicating significant overall enhancements in developers’ productivity. However, there exists a lack of design knowledge for organization-specific GAI systems to assist software development. To bridge this research gap, we derive a design framework for collaborative GAI systems in software development following design science research. Specifically, we conducted eight interviews with practitioners and reviewed extant literature to formulate design requirements and design principles. In our analysis of the literature and our qualitative data, we identify problems surrounding usability, data privacy, hallucination and transparency. To address these problems, we propose GAI system designs that enable user-centricity, data protection, quality control and communication. Our findings contribute valuable design knowledge to the field of generative AI and organizational software development practices.