Agentic Observability: Automated Alert Triage for Adobe E-Commerce

TL;DR

This paper introduces an agentic observability framework that autonomously performs alert triage in Adobe's e-commerce system, significantly reducing incident resolution time through AI-driven analysis and actions.

Contribution

It presents a novel autonomous alert triage system using a ReAct paradigm, improving efficiency and accuracy in enterprise incident response.

Findings

90% reduction in mean time to insight

Order-of-magnitude decrease in triage latency

Maintains diagnostic accuracy comparable to manual methods

Abstract

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.