Eric Schwartz argues that faster AI-assisted coding can leave teams with more complex production systems to troubleshoot. He describes the difficulty of tracing an incident across services and large volumes of operational data.
He sets out a progression from manual response and rules-based automationWorkflow automation uses software or AI to complete a connected sequence of routine steps with less manual effort. to agents that investigate individual services, diagnose issues across an environmentRoot cause analysis investigates the underlying conditions that produce a recurring problem, aiming to distinguish its causes from its visible symptoms. and eventually propose and verify fixesAgent completion verification checks evidence that an agent achieved the requested outcome rather than merely producing intermediate work..
Schwartz describes Traversal customer examples in alert triage and incident response, then outlines questions for evaluatingEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria. data access, search, system relationships and investigation speed. Product performance claims are presented as the speaker’s account.
Watch on YouTube




