Self-taught, came up on the tools, nine months into code and still going. Who I am, how I work, and the rules I run the crew under.
I started writing code in February 2026. Before that I’d never written a line.
I didn’t come up through a computer science degree, a bootcamp, or a tech job. I came up on the tools — mining, fishing, hospitality, retail, farming. Years on the frontline. I’ve seen how real businesses actually run, how a crew actually works, how a foreman keeps a job moving, and how things break when nobody’s paying attention.
I run AI agents the way I used to run crews.
I treat them like employees. They’re accelerators, not replacements. I’m still the one steering, still the one catching their mistakes, still the one signing off before anything ships. I give each one a name, a narrow job, a written role prompt, and a checkpoint it can’t skip.
A client hiring me isn’t hiring a junior coder catching up to other juniors. They’re hiring an operator who knows how to direct AI work and has nine months of receipts.
What I build now is built to last.
AI moves fast. Laws, regulations and pricing change month to month. So I’ve paused the projects that depend on all of that and put my focus on software and websites that keep working no matter what some vendor changes next quarter. The big builds taught me how to structure large work. Now I use that on things that hold up, like OPERATIONAL_CORE: business software with no AI inside, owned outright by the people who use it.
I used AI to build this page. I use AI on everything I can. And I read every word, checked every claim, and signed off on all of it — the same way a foreman signs off on a crew’s work before it leaves the site.
The skill was never typing every character myself. The skill is directing the work, catching what’s wrong before it ships, and standing behind what goes out the door.
I call it agentic living: AI agents doing the work on everything they can carry, while I stay the one who sets the job, checks the result and signs it off.
These aren’t theory. They came from real jobs where something went wrong and I wrote down the lesson so it wouldn’t happen twice.
The agents are Anthropic’s, off the shelf. What’s mine is the method around them — the role separation, the workflow rules, the prompt files, the checkpoints. The one real exception is WARD, inside L.I.LY: a genuine multi-agent safety system in code.
I’m not locked to one vendor. I mostly run Claude models day to day, but I’ve worked across Claude Code, Cursor, Cline, and Windsurf. The work is AI-assisted; the calls are mine.