I've spent 14+ years in software engineering, and the closer I've gotten to the work, the more I've become a builder first and a manager second. I run end-to-end: gathering requirements as an Engineering Manager, designing workflows and cloud architecture as an Architect, and writing the production code myself as a Full-Stack Developer. Owning the problem and shipping the solution is what I optimize for.

Around 2023 I started treating AI the same way I treat any tool: hands-on, pragmatic, and measured by whether it ships working code. That turned into a conviction I keep coming back to. The most effective engineering teams will be the ones who stop treating AI as a code generator and start wiring it into the loop: intent capture, closed feedback, and verification baked into the workflow itself.

• Autonomous AI coding sandboxes. Wiring remote agents into real workflows, including a spare laptop turned into an AI coding sandbox controlled from Telegram. Read the build →
• Closed-loop AI SDLC. Turning linear pipelines into reiterating loops: intent anchors, feature journals, and validation against live specs. Read how →
• Mindful LLM tools. Mottainai, an AI-powered purchasing decision tool built on a 220-line system prompt with zero cloud sync. See the project →
• This portfolio. An Astro 5 terminal-themed site, built (and rebuilt) with AI assistance, documented honestly. Read the build diary →

• Intent over output. AI-generated code needs a source of truth. A simple feature.md keeps agents honest about what they're actually building.
• Close the loop. Whatever you automate, you must be able to verify. Feedback loops, not pipelines.
• Ship on time. Requirements, architecture, and code are all one job. Owned end to end so nothing gets lost in handoff.
• Measure by outcomes. Sprint completion, latency, cost, availability. The numbers tell you whether the structure is right.

When I'm not building, I usually apply the same builder's mindset to things that have nothing to do with software: family, curiosity about cultures, and the kind of open-ended tinkering that keeps a 14-year career feeling like a hobby.

Curious how I think about systems and teams? The blog is where I write it down.