代理可观性：Adobe电子商务的自动化警报分拣
Agentic Observability: Automated Alert Triage for Adobe E-Commerce
AI总结：
本文提出了一种基于代理AI的自动化警报分拣框架，通过ReAct范式实现Adobe电子商务系统中警报分拣的自动化，显著提升分拣效率与诊断准确性。
摘要：
现代企业系统表现出复杂的相互依赖性，这使得可观性和事件响应变得越来越具有挑战性。手动警报分拣通常涉及日志检查、API验证和跨参考运营知识库，仍然是减少平均恢复时间（MTTR）的主要瓶颈。本文提出了一种部署在Adobe电子商务基础设施中的代理可观性框架，该框架使用ReAct范式自动执行警报分拣。在警报检测后，代理会动态识别受影响的服务，检索并分析分布式系统中的相关日志，并计划上下文相关的行动，如手册咨询、运行手册执行或最近部署代码的检索增强分析。生产部署的实证结果表明，与手动分拣相比，平均到洞察时间减少了90%，同时保持了可比的诊断准确性。我们的结果表明，代理AI能够实现分拣延迟的十倍减少和解决准确性的一次性飞跃，标志着企业运营向自主可观性转变的关键转折点。
英文摘要：
Modern enterprise systems exhibit complex interdependencies that make observability and incident response increasingly challenging. Manual alert triage, which typically involves log inspection, API verification, and cross-referencing operational knowledge bases, remains a major bottleneck in reducing mean recovery time (MTTR). This paper presents an agentic observability framework deployed within Adobe's e-commerce infrastructure that autonomously performs alert triage using a ReAct paradigm. Upon alert detection, the agent dynamically identifies the affected service, retrieves and analyzes correlated logs across distributed systems, and plans context-dependent actions such as handbook consultation, runbook execution, or retrieval-augmented analysis of recently deployed code. Empirical results from production deployment indicate a 90% reduction in mean time to insight compared to manual triage, while maintaining comparable diagnostic accuracy. Our results show that agentic AI enables an order-of-magnitude reduction in triage latency and a step-change in resolution accuracy, marking a pivotal shift toward autonomous observability in enterprise operations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
