Two decades of shipping software into production — scaling it, and making it survive failure. Lately: Agentic SDLC platforms, AI governance, and AI-native products — inside the enterprise and on my own.
The whole pipeline runs without hand-offs: CNN models trained on SageMaker, inference served across regions on ECS and SageMaker. It classifies hundreds of thousands of documents a day and is sized to absorb ten times that.
LessonScale is a design decision you make on day one, not a fire you fight later.
Vitu · 2025 — now
Making AI a safe tool for a whole company
An enterprise AI gateway with per-person budgets, usage tracking, and guardrails, so engineers and product managers can use Claude Code and Codex freely, within clear limits. Alongside it, a spec-driven way of building — specs generated from Jira, kept in sync with Confluence — now used across production projects.
LessonAdoption follows trust. Governance is what makes people comfortable moving fast.
Vehicle titling and registration runs on rules that differ by state and change constantly. Updating them used to be a weeks-long release. I designed an engine where they’re configured live — and where the UI renders itself from the rules — so changes ship in minutes and fewer transactions get stuck half-done.
LessonThe best systems let the business change without asking engineering.
Writing
Notes from building with AI — and leading the people who do.