700ms. That was the number that haunted my Kubernetes cluster, slowly burning it to the ground. Every alert the cluster generated, every log line it processed for AI-driven feedback, triggered an embedding operation.
“Why can’t I see the new photos?”
That’s how the outage started. Not with a PagerDuty alert or a Grafana dashboard turning red, but with a casual question from my wife.
April 2026 — one week of intensive AI-assisted work, one surprising bill, and one decision to do something about it
The Claude.ai usage screen showed €169.
April 2026 — on the gap between a well-researched plan and a wet crawl space
The design article made it sound rational. The build article made it sound competent.
April 2026 — field notes from wiring a Kubernetes SRE agent to Gemini 2.5 Flash
I spent the better part of two days debugging an AI agent that would reliably respond with… nothing.
