Orchestration logics for artificial intelligence platforms: From raw data to industry‐specific applications

Artificial intelligence (AI) platforms face distinct orchestration challenges in industry-specific settings, such as the need for specialised resources, data-sharing concerns, heterogeneous users and context-sensitive applications. This study investigates how these platforms can effectively orchestrate autonomous actors in developing and consuming AI applications despite these challenges. Through an analysis of five AI platforms for medical imaging, we identify four orchestration logics: platform resourcing, data-centric collaboration, distributed refinement and application brokering. These logics illustrate how platform owners can verticalize the AI development process by orchestrating actors who co-create, share and refine data and AI models, ultimately producing industry-specific applications capable of generalisation. Our findings extend research on platform orchestration logics and change our perspective from boundary resources to a process of boundary processing. These insights provide a theoretical foundation and practical strategies to build effective industry-specific AI platforms.     «

Artificial intelligence (AI) platforms face distinct orchestration challenges in industry-specific settings, such as the need for specialised resources, data-sharing concerns, heterogeneous users and context-sensitive applications. This study investigates how these platforms can effectively orchestrate autonomous actors in developing and consuming AI applications despite these challenges. Through an analysis of five AI platforms for medical imaging, we identify four orchestration logics: platfor...     »