Reliability And Failure Propagation In Ai-Generated Enterprise It Workflows: A Systematic Review And Conceptual Framework
Keywords:
AI-generated workflows, Reliability, Failure propagation, Enterprise IT, Systematic literature reviewAbstract
AI-generated enterprise IT workflows introduce reliability challenges arising from inaccurate generation, execution inconsistencies, and interconnected system dependencies. This study systematically reviews 40 studies selected from 150 identified records using a manual literature review and descriptive-comparative synthesis. Findings highlight potential failure propagation through shared data, automated decisions, API interactions, and dependent tasks, threatening operational continuity and data integrity. A five-component conceptual framework integrates workflow configuration, failure sources, propagation mechanisms, enterprise consequences, and reliability controls. The framework supports structured risk assessment and dependable workflow design, while future empirical validation remains necessary.
References
[1] Kourani, H., Berti, A., Schuster, D. and Van der Aalst, W.M., (2026). Evaluating large language models on business process modeling: framework, benchmark, and self-improvement analysis. Software and Systems Modeling, 25(4), pp.1151-1186.
[2] Gurram, A. (2024). A resilient framework for detecting and managing schema drift in evolving microservice contracts. International Journal of Intelligent Systems and Applications in Engineering.
[3] Arumilli, S. V. T. (2026). Maintaining human oversight within agentic artificial intelligence-driven workflows for enterprise operational decision-making and automated business process optimization systems.
[4] Kolukuri, N. R. (2025). Beyond dashboards: Designing decision-centric analytics systems that transform organizational decision-making.
[5] Mirani, A. (2026). AI-driven compliance intelligence: A conceptual framework for enterprise financial governance. Journal of Computational Analysis and Applications, 35(5), 116-131.
[6] Singh, V. (2026) ‘Real-time financial data validation platform for enterprise accounting systems’, International Journal of Computer Information Systems and Industrial Management Applications, 18(10s), pp. 467–481.
[7] Ricciardi Celsi, L. and McCann, J., (2026). Beyond Next-Token Prediction: A Standards-Aligned Survey of Autoregressive LLM Failure Modes, Deployment Patterns, and the Potential Role of World Models. Electronics, 15(5), p.966.
[8] Gurram, A. (2024). Data pipeline engineering framework for reducing hallucinations and improving reliability in large language model applications. European Journal of Advances in Engineering and Technology, 11(3), 176-187.
[9] Kolukuri, N. R. (2025). From reporting to reasoning: The evolution of enterprise decision-making through AI-enabled decision intelligence frameworks. International Journal of Advanced Multidisciplinary Research and Studies, 5(5), 1554-1562.
[10] Green, D.G., (2023). Emergence in complex networks of simple agents: DG Green. Journal of Economic Interaction and Coordination, 18(3), pp.419-462.
[11] Srinivas, S., Kirk, B., Zendejas, J., Espino, M., Boskovich, M., Bari, A., Dajani, K. and Alzahrani, N., (2025). AI-augmented SOC: A survey of LLMs and agents for security automation. Journal of Cybersecurity and Privacy, 5(4), p.95.
[12] Bhagwat, V.B. (2024) ‘A simplified transition from EBS Payroll to Cloud Payroll: Benefits and drawbacks’, Journal of Computational Analysis and Applications, 33(6), pp. 3725–3731.
[13] Fatouros, G., Mavrogiorgos, K., Makridis, G., Soldatos, J. and Kyriazis, D., (2026). LLM-Based Agents for Cybersecurity: A Systematic Review of Architectures, Applications, and Open Challenges. Journal of Cybersecurity and Privacy, 6(5), p.159.
[14] Koneni, C. and Lokula, S. (2026) ‘Evidence-quality telemetry for cloud incident response: Detecting gaps, drift, and integrity failures in large-scale observability pipelines’, in Proceedings of the 2026 14th International Symposium on Digital Forensics and Security (ISDFS). IEEE, pp. 1–6.
[15] Slotkienė, A. and Makaris, L., (2026). A Formal Trustworthiness Construct for Large Language Model-Based Test Generation: A Multidimensional Index Empirically Evaluated Through a Multi-Agent Study. Electronics, 15(16), p.3694.
[16] Singh, V. (2026) ‘Enterprise resource planning for financial applications: Engineering, architecture, and design principles’, International Journal of Scientific Research in Science and Technology, 13(2), pp. 653–661.
[17] Wang, Y., Pan, Y., Su, Z., Deng, Y., Zhao, Q., Du, L., Luan, T.H., Kang, J. and Niyato, D., (2025). Large model-based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends. IEEE Communications Surveys & Tutorials, 28, pp.1906-1949.
[18] Goyal, S., (2025). A critical review of agentic AI: Core technologies, applications, ethical implications, and future research directions. Jurnal Masyarakat Informatika, 16(2), pp.268-283.
[19] Koneni, C., Lokula, S. and Panjiyar, L. (2025) ‘A cloud-native approach to statistical anomaly detection and automated data-quality validation’, International Journal of Data Science and IoT Management System, 4(4), pp. 533–543.
[20] Bhagwat, V.B. (2025) ‘Simplifying payroll balance conversions in payroll systems implementation through the use of generative AI’, Journal of Information Systems Engineering and Management, 10(62s).
[21] Page, M., McKenzie, J., Bossuyt, P., Boutron, I., Hoffmann, T., Mulrow, C., Shamseer, L., Tetzlaff, J., Akl, E., Brennan, S. and Chou, R., (2024). Declaração PRISMA 2020: uma diretriz atualizada para publicação de revisões sistemáticas. Germinare, 4, pp.1-19.
[22] Xu, W., Huang, C., Gao, S. and Shang, S., (2025). LLM-Based Agents for Tool Learning: A Survey: W. Xu et al. Data Science and Engineering, 10(4), pp.533-563.
[23] Chowa, S.S., Alvi, R., Rahman, S.S., Rahman, M.A., Raiaan, M.A.K., Islam, M.R., Hussain, M. and Azam, S., (2026). From language to action: a review of large language models as autonomous agents and tool users. Artificial Intelligence Review, 59(2), p.71.
[24] Boominathan, S.A., Chintakunta, S.S., Guimaraes, E., Satyamurthy, K. and Nascimento, N., (2026). Empirical benchmarking of large language models for data science coding: a multidimensional evaluation. Empirical Software Engineering, 31(6), p.186.
[25] Zhang, P., Wu, J., He, H., Yan, L. and Li, W., (2026). Topo-MFP: Topology-aware multimodal propagation learning for fault detection and root cause localization in microservice systems. Journal of King Saud University Computer and Information Sciences, 38(7), p.780.
[26] Phillips, M., Reed, J.B., Zwicky, D. and Van Epps, A.S., (2024). A scoping review of engineering education systematic reviews. Journal of Engineering Education, 113(4), pp.818-837.
[27] Mancin, S., Sguanci, M., Andreoli, D., Soekeland, F., Anastasi, G., Piredda, M. and De Marinis, M.G., (2024). Systematic review of clinical practice guidelines and systematic reviews: a method for conducting comprehensive analysis. MethodsX, 12, p.102532.
[28] Arumilli, S. V. T. (2026). An empirical analysis of reliability challenges in multi-step agentic AI systems. Journal of Information Systems Engineering and Management, 11(3s).
[29] Shi, C., Luan, X., Jiang, S. and He, B., (2026). Trustworthy Imagination in Embodied World Models: Structural Constraints, Reality Anchoring, and Trust Adjudication. SmartBot, p.e70074.
[30] Singh, V. (2026) ‘Dynamic AI tool orchestration framework for enterprise-scale AI agents’, Journal of Information Systems Engineering and Management, 11(3s), pp. 2123–2131.
[31] Farfoura, M., Alia, M., Mashal, I., Hnaif, A. and Odeh, M., (2026). The Double-Edged Sword of AI Pair Programmers: A Systematic Literature Review of Security Vulnerabilities in AI-Generated Code and Agentic Development Environments. Journal of Sustainable Smart Systems in Education & Environment, 1(2), pp.24-63.
[32] Cederbladh, J., Cicchetti, A. and Suryadevara, J., (2024). Early validation and verification of system behaviour in model-based systems engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(3), pp.1-67.
[33] Jensen, D., Van Bossuyt, D.L., Bello, O., O’Halloran, B.M. and Papakonstantinou, N., (2024). A survey of function failure identification and propagation analysis methods for system design. Journal of Computing and Information Science in Engineering, 24(9), p.090801.
[34] Ekundayo, F., (2024). Leveraging AI-driven decision intelligence for complex systems engineering. Int J Res Publ Rev, 5(11), pp.1-10.
[35] Sahu, R., (2025). Enterprise knowledge graphs: Revolutionizing system dependencies. Journal Of Engineering And Computer Sciences, 4(8), pp.940-948.
[36] Srivastava, I., Bhat, S., Vardhan, B.S. and Bokde, N.D., (2022). Fault detection, isolation and service restoration in modern power distribution systems: A review. Energies, 15(19), p.7264.
[37] Melaku, H.M., (2023). A dynamic and adaptive cybersecurity governance framework. Journal of Cybersecurity and Privacy, 3(3), pp.327-350.
[38] Todupunuri, A. (2024) ‘Artificial intelligence ethics: Investigating ethical frameworks, bias mitigation, and transparency in AI systems to ensure responsible deployment and use of AI technologies’, International Journal of Innovative Research in Science, Engineering and Technology, 13(9), pp. 1–14. doi: 10.15680/IJIRSET.2024.1309002.
[39] Lee, K.M., (2025). Real-Time Enterprise Data Integration Using Event-Driven Architecture and Secure Cloud Connectivity Through Microservices Orchestration. International Journal of Computer Technology and Electronics Communication, 8(6), pp.12041-12049.
[40] Kasneci, G. and Kasneci, E., (2026). The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems. AI and Ethics, 6(3), p.295.
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence and Communication Networks
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
