Traversal's 5 Levels of Self-Driving Production: Why Coding Agents Make Ops Harder
AI Engineer · youtube · 2026-10-03
At AI Engineer World's Fair 2026, Traversal PM Eric Schwartz explains why coding agents made production harder to debug: more AI-written code means more troubleshooting time.
- Observability dashboards tell you what broke, not why — root cause analysis is a causal problem, not an observability one, and multi-hop failures are hard for both humans and LLMs.
- He lays out five levels of "self-driving production," from war rooms to closed-loop fixes.
- Case studies: alert intelligence for a PepsiCo supply chain team and incident RCA at American Express.
- Closes with five questions to ask any AI SRE.
More from coding & agent
- FT: US tech outages blamed on rush to fix bugs found by AI — nordicinst · 2026-11-19
- Claude Code overtakes Cursor and Copilot in job-post mentions ahead of Anthropic IPO — antgoldbloom · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19
- Orchestrator's Cloud Agents graduate from beta to general availability — julianweisser · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19