Human-Governed Artificial Intelligence Agents for Intelligent Incident Triage in Private Cloud Environments
Keywords:
AIOps, event-driven automation, human-AI collaboration, incident triage, private cloud infrastructure, software-defined data center managementAbstract
Governance architecture, not model capability, determines whether artificial intelligence agents improve or complicate incident triage outcomes in enterprise private cloud environments. Software-defined data center (SDDC) platforms integrate virtualization, microservices, container orchestration, and AI inference workloads into unified operational ecosystems — each component generating distinct telemetry that engineers must synthesize manually when incidents occur. The result is an information-retrieval bottleneck that extends mean time to triage in proportion to infrastructure scale and heterogeneity. This article proposes a three-tier agent authorization framework that distinguishes agent-eligible knowledge retrieval from human-supervised diagnostic tasks and human-only remediation decisions. An event-driven dispatch mechanism connects infrastructure monitoring telemetry to agent workflows without requiring manual initiation, while a retrieval-augmented generation (RAG) layer grounds all agent outputs in cited operational documentation. Evidence from published AIOps deployments indicates measurable reductions in mean time to triage and knowledge retrieval latency when governance boundaries are explicitly designed into agent workflows. The framework is directly applicable to SDDC lifecycle management environments where event-driven automation infrastructure already exists, enabling incremental AI agent adoption without redesigning operational accountability structures.
Downloads
References
Cisco, "What is AIOps?," HMD Praxis der Wirtschaftsinformatik, vol. 56, no. 5, pp. 345–346, 2019. https://www.cisco.com/site/us/en/learn/topics/artificial-intelligence/what-is-aiops.html
L. Ben-Shimol, O. Raz, G. Mishne, and M. Shanbhag, "Observability and Incident Response in Managed Serverless Environments Using Ontology-Based Log Monitoring," IEEE Trans. Cloud Comput., 2025. https://ieeexplore.ieee.org/document/11122875
H. L. Boddupally, "Automating Incident Triage and Root Cause Intelligence Through Large Language Model–Driven Correlation of System Logs and Operational Metrics in Large-Scale Distributed Environments," Int. J. Eng. Extended Technol. Res. (IJEETR), vol. 5, no. 6, 2023. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6736978
T. Ahmed, S. Ghosh, C. Bansal, T. Zimmermann, X. Zhang, and S. Rajmohan, "Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models," in Proc. 2023 IEEE/ACM 45th Int. Conf. Softw. Eng. (ICSE), 2023. https://arxiv.org/abs/2301.03797
H. Zhang, "A Unified AIOps Pipeline for Joint Log–KPI Anomaly Detection, Graph-Based Root Cause Localization, and LLM-Generated Runbooks," J. Adv. Comput. Syst., vol. 4, no. 1, 2024. https://scipublication.com/index.php/JACS/article/view/277
Y. Chen, Z. Kang, C. Liu, T. Li, Y. Su, Y. Zhao, X. Qu, Y. Xu, C. Bi, Z. Wang, and X. Zhang, "Automatic Root Cause Analysis via Large Language Models for Cloud Incidents," in Proc. Nineteenth Eur. Conf. Comput. Syst. (EuroSys '24), ACM, 2024. https://arxiv.org/abs/2305.15778
J. Zha, X. Shan, J. Lu, J. Zhu, and Z. Liu, "Leveraging Large Language Models for Efficient Alert Aggregation in AIOPs," Electronics, vol. 13, no. 22, p. 4425, 2024. https://www.mdpi.com/2079-9292/13/22/4425
A. Rahmatulloh, F. Nugraha, R. Gunawan, and I. Darmawan, "Event-Driven Architecture to Improve Performance and Scalability in Microservices-Based Systems," in 2022 IEEE Int. Conf. Advancement in Data Science, E-learning and Information Systems (ICADEIS), pp. 01–06, 2022. https://ieeexplore.ieee.org/document/10037390
Z. Purfallah Mazraemolla and A. Rasoolzadegan, "An effective failure detection method for microservice-based systems using distributed tracing data," Eng. Appl. Artif. Intell., 2024. https://www.sciencedirect.com/science/article/abs/pii/S0952197624007164
M. Raeiszadeh, A. Ebrahimzadeh, A. Saleem, R. H. Glitho, J. Eker, and R. A. F. Mini, "Real-Time Anomaly Detection Using Distributed Tracing in Microservice Cloud Applications," in 2023 IEEE 12th Int. Conf. Cloud Networking (CloudNet), 2023. https://lup.lub.lu.se/search/files/165150749/Real_Time_Anomaly_Detection_Using_Distributed_Tracing_in_Microservice_Cloud_Applications.pdf
S. Zhang, D. Fan, and L. He, "Large Language Models Empowered Online Log Anomaly Detection in AIOps," in Proc. 2024 31st Asia-Pacific Softw. Eng. Conf. (APSEC), pp. 402–411, 2024. https://ieeexplore.ieee.org/document/10967310
X. Wang, X. Liu, P. Xu, and H. Du, "Graph-based Anomaly Detection and Root Cause Analysis for Microservices in Cloud-Native Platform," in 2024 IEEE Int. Conf. Sustainable Computing and Communications (SustainCom), 2024. https://ieeexplore.ieee.org/document/10917910
R. D'Antonio and H. Xie, "Human-in-the-Loop Runbook Improvement with Agentic Support Automation," in 2025 IEEE 7th Int. Conf. Cognitive Machine Intelligence (CogMI), 2025. https://ieeexplore.ieee.org/document/11417021
Y. Zhang, X. He, X. Zheng, M. Qiu, Q. Lin, H. Zhang, Q. Zhang, L. Li, S. Dang, M. R. Lyu, and D. Zhang, "CloudRCA: A Root Cause Analysis Framework for Cloud Computing Platforms," in Proc. 30th ACM Int. Conf. Inf. & Knowl. Mgmt. (CIKM), pp. 4107–4116, 2021. https://arxiv.org/abs/2111.03753
L. An, A.-J. Tu, X. Liu, and R. Akkiraju, "Real-time Statistical Log Anomaly Detection with Continuous AIOps Learning," in Proc. 12th Int. Conf. Cloud Comput. and Services Sci. (CLOSER), 2022. https://www.scitepress.org/Papers/2022/110692/110692.pdf
L. M. Barata, S. Sequeira, E. Lopes, P. R. M. Inácio, and M. M. Freire, "Anomaly detection and root-cause identification in microservices: a survey," Cluster Comput., Springer, 2026. https://link.springer.com/article/10.1007/s10586-026-06095-9
P. Moens, B. Andriessen, M. Sebrechts, B. Volckaert, and S. Van Hoecke, "Edge Anomaly Detection Framework for AIOps in Cloud and IoT," in Proc. 13th Int. Conf. Cloud Comput. and Services Sci. (CLOSER), 2023. https://www.scitepress.org/Papers/2023/118386/118386.pdf
D. Toprani and V. K. Madisetti, "LLM Agentic Workflow for Automated Vulnerability Detection and Remediation in Infrastructure-as-Code," IEEE Access, 2025. https://ieeexplore.ieee.org/document/10965635
M. Soualhia and F. Wuhib, "Automated Traces-based Anomaly Detection and Root Cause Analysis in Cloud Platforms," in 2022 IEEE Int. Conf. Cloud Engineering (IC2E), 2022. https://ieeexplore.ieee.org/document/9946356
X. Peng, "Large-Scale Trace Analysis for Microservice Anomaly Detection and Root Cause Localization," in Proc. Federated Africa and Middle East Conf. Softw. Eng. (FAMSE), 2022. https://dl.acm.org/doi/10.1145/3531056.3542765
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
