On-Call Without Burnout: Rotations, Runbooks, and Escalation
Our best engineer quit citing on-call. We rebuilt the whole thing: saner rotations, runbooks that actually help at 3am, and escalation that doesn't punish asking for help.
Topics
Latest Articles
View All →LLM Output Validation: Schema-First Prompt Engineering Patterns
We invalidate ~6% of LLM outputs before they reach a downstream system. Here's how we structure prompts and validators to catch malformed responses early.
Argo Rollouts: Canary Deployments That Caught a $40k Bug
A two-line config change to an Argo Rollouts analysis template caught a regression that would have cost ~$40k in API spend before we noticed. Here's the pattern.