Although agile management practices offer advantages such as flexibility and speed, their excessive or improper implementation can lead to agile fatigue, negatively affecting organizational efficiency and employee performance. While the literature extensively examines the antecedents of agile fatigue, studies that systematically prioritize prevention strategies across different organizational contexts remain limited. Therefore, this study aims to identify strategic priorities for preventing agile fatigue and to develop an AI-based fuzzy multi-criteria decision-making framework to support objective and data-driven decision-making from a cross-sectoral perspective rather than focusing on a single industry. The proposed model employs AI-supported natural language processing (NLP) and rule-based decision logic to automatically extract key concepts from literature summaries and generate a structured criteria set. Expert opinions obtained from a limited but heterogeneous group of agile-experienced professionals are weighted based on demographic characteristics using the z-score based normalized ideal distance method (z-NIDM), while criteria weights are calculated via the CRITIC method and strategic alternatives are ranked using the ARLON method. The framework integrates Sierpinski Triangle, Pythagorean, and Fermatean fuzzy sets to model uncertainty in a robust and comparative manner. The findings indicate that business process flexibility (0.178) and cultural adaptation and communication (0.169) are the most critical criteria, while culture and communication strategies (0.194) and business process and structural strategies (0.168) emerge as the most effective interventions. From a practical perspective, these results provide analytically grounded and transferable guidance for managers across different industries by prioritizing structural and cultural actions over isolated technological or training initiatives, offering a strategic roadmap for sustainable agile transformation and the prevention of agile fatigue without claiming universal generalizability.
Eti et al. (2026) studied this question.