1 views collected around this technical thread.
This article explores how AI agents powered by large models can predict failures, perform root‑cause analysis, enhance knowledge‑based Q&A, automate change releases, and enable intelligent decision‑making, dramatically improving efficiency and reliability in modern IT operations.
This article presents the goals, methods, and evolution of Qunar's operations team in reducing application failures, improving reliability through fault definition, rapid repair, automation, and AIOps-driven fault prediction, while sharing lessons from industrial PHM and outlining future challenges.
This article outlines Qunar's operational strategy for reducing failures and extending uptime through precise fault detection, rapid recovery, and AI-powered predictive health management, detailing the evolution of their OPS processes, practical implementations, and future challenges in applying PHM to internet services.
The talk by chief architect Luo Hao explains how China Aviation Information tackles heavy legacy systems, non‑standard architectures, and zero‑downtime requirements by using AIOps techniques such as automated configuration discovery, cluster analysis, fault prediction, anomaly detection, event compression and rapid root‑cause automation.
This talk explains how China Aviation Information applies practical AIOps techniques—such as automated configuration management, cluster analysis, fault prediction, anomaly detection, and event compression—to achieve near‑zero downtime in a complex, legacy‑heavy ticketing and travel system.