All Posts
JAPIE: How an Incoherent Mess Became a Self-Improving AI Orchestrator
April 2026 — on shipping fast, discovering chaos, systematically fixing it, and then building a system that improves itself
There’s a particular kind of technical debt that emerges when you ask an LLM to design an AI orchestrator without a clear spec. The result lands in your codebase looking plausible: proper error handling, metrics collection, a learning loop. But when you actually try to run it against real workflows, you discover the wires are loose, the assumptions are broken, and half the system assumes the other half already exists.
cluster-shepherd: The AI Ops Agent That Actually Knows Your Cluster
April 2026 — what happens when you stop treating AI as a search engine and start treating it as a co-pilot with real cluster access
I built an AI to stop the wrong recruiters from wasting my time
April 2026 — on replacing an inbox full of irrelevant opportunities with a system that actually thinks
If you’ve worked in IT for more than a few years in Europe, you know the pattern. A recruiter reaches out. The message contains your name (sometimes), a job description (loosely relevant), and an offer (usually well below your rate). They’re matching on keywords. “Kubernetes” in your profile, “Kubernetes” in the job description — match. The fact that the role is junior, six timezones away, pays 40% less than your current work, and requires a technology you haven’t touched in three years is irrelevant. The keyword matched.