About me and my work

I’m an AI Operations Architect. I help teams turn business know-how into AI systems that run day-to-day operations, with people in control when it matters.

The point is not to remove people from the work. It is to give them better leverage where judgment matters.

I have worked in technology for more than seven years, including at Uber (opens in a new tab), Kahoot! (opens in a new tab), and Gelato (opens in a new tab). The common thread has been making complex operational work easier to understand, improve, and run.

The kind of work I do

I work with teams that need more than a quick automation. The goal is a system that can carry useful work: clear inputs, defined ownership, appropriate permissions, and a way for people to step in when judgment is needed.

I have shipped dozens of Make (opens in a new tab) and n8n (opens in a new tab) workflows inside an ISO 27001-certified company. That made governance, auditability, and error recovery part of the work from the start.

How I work

I begin with the operating reality: the people doing the work, the decision that needs to be made, and the point where an automated system should pause or escalate. From there, I make the delivery path concrete enough to build, evaluate, and improve.

Today, I build AI operating systems and custom MCP (opens in a new tab) connectors, using Cloudflare (opens in a new tab) and Supabase (opens in a new tab) as my default stack. I use Claude Code (opens in a new tab) and Codex (opens in a new tab) to move from an operating problem to a working custom system quickly, while keeping the important boundaries explicit.

Working together

I’m currently available for projects and consulting. If you’re considering an AI initiative, email me and we can see whether we’re a good fit and where I can help.