The 5 Levels of Self-Driving Production — Eric Schwartz, Traversal

Coding agents made development faster. They also made production a lot harder to debug. Eric Schwartz, product manager at Traversal, explains why more AI-written code means more time spent troubleshooting, why observability dashboards tell you what broke but not why, and why root cause analysis is a causal problem rather than an observability problem. He lays out five levels of 'self-driving production' and shares case studies on alert intelligence for a PepsiCo supply chain team and incident root cause analysis at American Express. He closes with five questions to ask any AI SRE. In this talk: • How coding agents shift engineering time from building to troubleshooting • Why multi-hop root cause analysis is so hard for humans and LLMs • The five levels of self-driving production, from war rooms to closed-loop fixes • Five questions for evaluating an AI SRE SPEAKER Eric Schwartz, Product Manager, Traversal LinkedIn: https://www.linkedin.com/in/ericschwartz30/ LINKS Traversal: https://www.traversal.com Self-Driving Production (blog): https://www.traversal.com/blog/self-driving-production CHAPTERS 0:00 Intro 0:12 Agenda 1:02 How coding agents changed the SDLC 2:02 More code, more troubleshooting 2:32 The cost of troubleshooting 3:12 Why observability tools stop short 4:01 Even LLMs struggle with root cause 4:31 Why root cause is hard: multi-hop failures 5:46 Root cause is a causal problem 6:26 Self-driving production, defined 7:06 The five levels of autonomy 8:50 Traversal at enterprise scale 9:35 Use cases 11:05 Case study: alert intelligence at PepsiCo 12:55 Case study: incident RCA at American Express 14:44 Five questions to ask an AI SRE 16:39 Traversal's stack 17:39 Production world model and causal search Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #SRE #AIOps #AIEngineer