Year: 2026
Type: conference-paper
Abstract: Despite the interest in Artificial Intelligence (AI) within manufacturing, many companies struggle to move beyond experimental pilot projects toward successful operational integration. A significant gap remains between the acquisition of technical tools and the development of the organizational capability to use them effectively in a production environment. This study investigates how AI coding assistants can bridge this gap by empowering non-programming domain experts, such as process engineers and quality technicians, to achieve analytical autonomy. A case study with an interactive approach was applied at a heavy-duty automotive manufacturing site. The researchers and practitioners engaged in a joint learning process for six months. The findings are analyzed through the lens of dynamic capabilities theory, specifically the capacities for Sensing , Seizing , and Reconfiguring . Results reveal a trust-adoption paradox, where participants overcome skepticism of AI-generated outputs by leveraging their domain expertise for verification. The study documents six real-world cases where participants independently used AI tools to identify bottlenecks, optimize cycle times, and improve data quality. Our findings suggest that AI coding assistants act as a capability multiplier, reducing cross-functional friction and initiating a virtuous cycle of data integrity. For management, the study implies that the AI integration hurdle can be overcome not by hiring external specialists, but by providing the autonomy and technical support for the existing workforce to translate their domain knowledge into executable digital solutions.
Institutions: Mälardalen University, Volvo (Sweden)
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
Funder: Mälardalens högskola
OpenAlex ID: W7214560697