Thoughts on building AI-native systems, getting models to production, and the work that actually matters.
Everyone says they're doing AI. Most are bolting it on. Here's what it looks like when you build it in from day one.
How we replaced threshold-based alerting with anomaly detection and cut alert noise by 70% — a case study in AI-native ops.
The gap between a working demo and a production system is where most AI initiatives die. Here's what actually goes wrong.
New posts and insights, no spam. Unsubscribe anytime.