一句话：在 Red Hat OpenShift 上实践 LLM 智能体驱动的 AIOps，用工具增强推理整合预测模型以自动化运维任务。
本文是一份在 Red Hat OpenShift 上开展的工业经验报告，探讨如何将大语言模型（LLM）落地到真实的 Kubernetes 云原生运维场景中。作者指出，虽然 AIOps 在自动化工作流、提升效率与辅助决策方面潜力巨大，但实际部署仍受制于数据质量问题、云原生环境的复杂性以及运维团队的技能缺口。为此，论文利用 LLM 的自然语言理解能力分析日志、事件报告与技术文档等非结构化数据，并通过工具增强推理（tool-augmented reasoning）将预测式机器学习模型与 LLM 智能体集成，从而自动化 IT 任务、增强可观测性并减轻运维人员负担。报告最后总结了 LLM 在生产级 AIOps 场景中的能力边界与局限，为后续研究与实践提供经验参考。
The integration of Artificial Intelligence (AI) into IT Operations Management (ITOM), commonly referred to as AIOps, offers substantial potential for automating workflows, enhancing efficiency, and supporting informed decision-making. However, practical implementation of AI within IT operations remains challenging, particularly due to data quality issues, the complexity of cloud-native environments, and skill gaps within operational teams. The emergence of Large Language Models (LLMs) presents new opportunities to address these barriers by leveraging their advanced natural language understanding, enabling the analysis of unstructured data such as logs, incident reports, and technical documentation. In this paper, we present an industry experience report conducted on Red Hat OpenShift to explore how LLMs can be operationalized in real-world Kubernetes-based environments. We integrate predictive machine learning models with LLM agents through tool-augmented reasoning, highlighting novel methods to automate IT tasks, enhance observability, and reduce operator burden. Our findings provide insights into both the capabilities and limitations of LLMs in production-grade AIOps scenarios.