TYRIEN JONES AI ENGINEER · FOREMAN
WHO I AM

About

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.

00 · WHO I AM

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.

01

Yes, I used AI to make this. That’s the point.

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.

02

The rules I run the crew under

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.

01
Working version first, polish second.Ship the plain, mechanical, operator-checked version first. Make it nice after it works.
02
One thing at a time.On staged work, I stop between batches and wait for the go-ahead.
03
Test the fix against real data before I write it.Replay it against what’s actually on disk, check the data flow, stress the design — before a line of the fix gets written.
04
A fix that doesn’t hold means I’ve got the wrong problem.I don’t keep swinging at the same spot. I go back and prove what’s actually broken before I touch the code again.
05
Hostile-input test before “done.”Anywhere a user or a file can put text into the system, I throw bad input at it on purpose.
06
Say up front whether a file is safe to delete.Every scratch file gets that call made out loud.
07
Write it down so the next person can pick it up cold.Human or agent. Handover docs, current-state files, decision logs, audit trails.

If you’ve worked a site, you’ll recognise the shape: a written brief before the work starts, a sign-off before it leaves, and a record the next person can pick up. It’s on the job sheets: handovers and an append-only ledger on ETS2LA, decision logs on L.I.LY, a hard sign-off gate on ECO.

03

How I work with AI — the crew

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.

SAME SHAPE EVERY TIME
MARCH
Stability Forge
Alex (engine), Sarah (wrapper), TALLAS (read-only audit)
MARCH
HuntOS 4.0
David, Heather
MARCH
Combat sim
Kade Orion (systems builder)
MAR–JUN
ECO
Talos (strategy and audit), Effy (build)
MAY–JUN
L.I.LY
Build agents working slice by slice, and fresh agents hostile-reviewing every slice until it came back clean
MAY–JUN
ETS2LA
Director (Talos), Auto Drive Agent, Auto Drive Strategist
JUNE
OPERATIONAL_CORE
A lead agent writing each job up, build agents, and a separate audit before every phase was sealed
JUN–OCT
PC Control Hub
A lead build agent and a helper, each under its own named role and sign-off

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.

WORK WITH ME That’s how I work. If it’s the kind of operator you need —
LET’S TALK ABOUT THE JOB →