Modern decentralized organizational platforms, particularly those built on distributed cloud-native and microservices architectures, face increasing complexity in maintaining operational resilience. Failures in such systems are often non-linear, multi-factorial, and difficult to diagnose due to the absence of centralized control and the presence of heterogeneous telemetry sources. This research proposes a conceptual and analytical framework for root-cause knowledge extraction (RCKE) enhanced by generative AI techniques to enable automated resilience in decentralized organizational platforms.

The study synthesizes advancements in generative artificial intelligence, deep learning, and system-level fault analysis to construct an integrated model capable of identifying latent failure dependencies, extracting causal knowledge from system logs, and enabling autonomous recovery mechanisms. Prior work demonstrates that generative models, particularly GANs and diffusion-based architectures, can significantly enhance data synthesis and diagnostic precision in medical imaging domains (Akbar et al., 2024; Alalwan et al., 2024). These findings are extended into the domain of distributed system resilience, where synthetic data generation and pattern reconstruction are essential for diagnosing rare or unseen system failures.

Furthermore, recent research emphasizes the role of generative AI in complex adaptive systems, including brain-computer interfaces and medical decision systems, highlighting its capacity for contextual reasoning and pattern abstraction (Eldawlatly, 2024; Celard et al., 2023). Building upon these foundations, this paper introduces a structured framework that combines causal inference graphs, large language models (LLMs), and Kubernetes-based self-healing mechanisms to automate root-cause detection and remediation.

A critical dependency in this framework is the integration of post-mortem analytical intelligence for system recovery, as highlighted in recent studies on multi-cloud self-healing systems (Post-Mortem Intelligence for Self-Healing Multi-Cloud Enterprise Applications Using LLMs and Kubernetes, 2026), which underscores the importance of retrospective learning for continuous resilience improvement.

The proposed approach contributes to the fields of distributed computing, artificial intelligence, and organizational systems engineering by offering a unified methodology for automated fault diagnosis, knowledge extraction, and resilience orchestration in decentralized environments.

Root-cause analysis, generative AI, decentralized systems, automated resilience

Akbar, M. U. Larsson, I. Blystad, and A. Eklund, “Brain tumor segmentation using synthetic MR images-A comparison of GANs and diffusion models,” Sci. Data, vol. 11, no. 1, p. 259, 2024.

N. Alalwan, A. Alwadain, A. I. Alzahrani, A. H. Al-Bayatti, A. Abozeid, and R. M. Abd El-Aziz, “Advancements in brain tumor identification: integrating synthetic GANs with federated-CNNs in medical imaging analysis,” Alexandria Eng. J., vol. 105, pp. 105–119, 2024.

A. Anaya-Isaza, L. Mera-Jiménez, L. Verdugo-Alejo, and L. Sarasti, “Optimizing MRI-based brain tumor classification and detection using AI: a comparative analysis of neural networks, transfer learning, data augmentation, and the cross-transformer network,” Eur. J. Radiol. Open, vol. 10, p. 100484, 2023.

P. Celard, E. L. Iglesias, J. M. Sorribes-Fdez, R. Romero, A. S. Vieira, and L. Borrajo, “A survey on deep learning applied to medical images: from simple artificial neural networks to generative models,” Neural Comput. Appl., vol. 35, no. 3, pp. 2291–2323, 2023.K. Elissa, “Title of paper if known,” unpublished.

S. Eldawlatly, “On the role of generative artificial intelligence in the development of brain-computer interfaces,” BMC Biomed. Eng., vol. 6, no. 1, p. 4, 2024.

Philip, P. G. (2025). Predictive Maintenance Approach for Electric Power Systems Using Machine Learning. The American Journal of Interdisciplinary Innovations and Research, 7(09), 145–160. Retrieved from https://theamericanjournals.com/index.php/tajiir/article/view/ml-predictive-maintenance-power-systems

N. Ghebrehiwet, N. Zaki, R. Damseh, and M. S. Mohamad, “Revolutionizing personalized medicine with generative AI: a systematic review,” Artif. Intell. Rev., vol. 57, no. 5, p. 128, 2024.).

Gong, C. Jing, X. Chen, C. M. Pun, G. Huang, A. Saha,… and S. Wang, “Generative AI for brain image computing and brain network computing: a review,” Front. Neurosci., vol. 17, p. 1203104, 2023.

U. Humayun, M. T. Yaseen, A. Shahwaiz, and A. Iftikhar, “Deep learning approaches for brain tumor detection and segmentation in MRI imaging,” J. Comput. Biomed. Inform., vol. 8, no. 1, 2024.

A. Kaur, M. Mittal, J. S. Bhatti, S. Thareja, and S. Singh, “A systematic literature review on the significance of deep learning and machine learning in predicting Alzheimer's disease,” Artif. Intell. Med., vol. 154, p. 102928, 2024.

P. Kaur, R. Ali, G. Kaur, J. S. Bhatti, and S. Singh, “Enhancing early Alzheimer's diagnosis through machine learning on multimodal neuroimaging and cognitive data,” Iran J. Comput. Sci., 2025, doi: 10.1007/s42044-025-00282-4.

P. Raut, G. Baldini, M. Schöneck, and L. Caldeira, “Using a generative adversarial network to generate synthetic MRI images for multi-class automatic segmentation of brain tumors,” Front. Radiol., vol. 3, p. 1336902, 2024.

S. Singh, P. Mittal, and K. S. Kahlon, “Empirical model for predicting high, medium and low severity faults using object oriented metrics in Mozilla Firefox,” Int. J. Comput. Appl. Technol., vol. 47, no. 2–3, pp. 110–124, 2013.

Puram, S. (2026). Post-Mortem Intelligence for Self-Healing Multi-Cloud Enterprise Applications Using LLMs and Kubernetes. International Journal of Research and Applied Innovations, 9(1), 13641-13649.