TYRIEN JONES AI ENGINEER · FOREMAN
PORTFOLIO / ECO
L.I.LY’S BIG BROTHER 0.1.0 · PHASES 1–3 COMPLETE · PAUSED

ECO

A local-first control plane for governing AI-assisted builds on long, complex jobs.

BUILTMar – Jun 2026
STATUSPaused · to be rebuilt
COMMITS279
RUST TESTS678 passed, 0 failed
CREWTalos · Effy
VERIFIED450+ PROOFS
ECO's main screen with a project open at trust level L0, read only, and the AI set to respond only. ECO's answer names the exact file and function it would change, what it would replace and why, with the model, tokens and cost logged underneath.
MAIN SCREEN · TRUST LEVEL READ-ONLY · AI SET TO RESPOND ONLY · LAST BUILD, RUNNING ON MY PC
00 · IN PLAIN TERMS

ECO is a dedicated workspace for getting real software built with AI — with you in charge the whole way. It keeps the AI on a leash so it can take on long, complicated jobs without wandering off or quietly breaking things, and nothing it does counts until you’ve checked it and signed off.

My biggest project, and the one I’m proudest of. It’s paused, and I’m not going to pretend otherwise. What it gave me is the hard part: how to structure and run a build this big. When I pick it back up, I’ll rebuild it from scratch with that knowledge instead of patching what’s there.

01

The job

When a build runs long and the work gets complex, it goes sideways in the same few ways every time. Different AI models end up touching the same code — and it still has to read like one hand wrote it. The truth about where things stand gets scattered across chat windows that vanish the moment you close them. And the second you let the agents run themselves, you lose the thread on what was actually checked.

WHAT ECO HOLDS IN LINE
AOne verified place where the truth lives. BThe human as the final word on every commit, every decision, every risk. CVerification proofs treated as real artifacts, with their freshness tracked. DA bounded run → write-back → re-run → mark-verified lifecycle that’s approval-gated, not turned loose.

No off-the-shelf tool does this. That’s why I had to build it.

02

What’s mine

Nearly all of ECO is my design. The code itself is AI-written under my direction and my checkpoints; the architecture, the calls, and the governance are mine. It all runs local, on my machine, not someone’s cloud.

BEFORE · RULES IN A DOC Markdown the AI is supposed to follow. Rules in a doc can be skipped, forgotten, or argued around.
AFTER · RULES IN THE CODE Rust the AI has to pass through. Governance rules enforced in Rust and SQLite. Once it’s in the binary, the agent can’t talk its way past it — it has to go through it.
03

Wired in

Less than the other projects — but not nothing. There’s a provider layer so ECO can run against mock AI or live, and swap between vendors: Anthropic is the daily driver, but there’s a proven live run on OpenAI too (VERIF-182), so this one isn’t tied to a single AI company.

MATERIALS LIST
Tauri
Desktop shell
MY DESIGN
Rust
Backend + codified governance
MY DESIGN
SvelteKit
Front end
MY DESIGN
SQLite + FTS
Store with full-text search; indexer that reads existing folders without moving a file
MY DESIGN
Anthropic · OpenAI
Model providers, swappable
WIRED IN
04

How I ran it

The agent setup isn’t a quirk — it’s the shape complex work needs. Any well-run shop splits it the same way: someone plans, someone builds, and the boss signs off on both. The agents are off the shelf; the framework around them — the roles, the separation, the rules, the checkpoints — is mine.

STRATEGY & AUDITTalos
THE BUILDEffy
FINAL SAYMe

The pre-commit review is a hard stop. Nothing gets committed without my sign-off.

05

The receipts

A verification log that’s the real spine of the project — each proof noting what it does and doesn’t prove. Those receipts live in the verification log, not in git history.

LEDGERSOURCE: VERIFICATION LOG
450+numbered proofs in the verification log 678Rust tests passed, zero failed, on the last full run 279commits, March to June 2026 End to endRun → write back → re-run → mark verified, proven under both a mock AI and a live one
ONE EXAMPLE OF THE DISCIPLINE · MAIN SCREEN
~8,912lines, before
→
~1,959lines, today
Thirteen passes, each one regression-proven before the next. No “trust me, it still works.”
06

Why it counts

It’s the biggest thing I’ve built, and it’s solving a problem I couldn’t find solved anywhere else. Building it is how I learned to structure big work: keep a long, multi-agent job coherent, keep a human in charge of every call, and prove what’s been checked instead of hoping. Pausing it was a call too. I’d rather rebuild it clean than keep patching.

If a client’s got a build that’s going to run for months across more than one AI, this is the kind of control I bring to it.

WORK WITH ME Got a long build that has to stay coherent across more than one AI?
LET’S TALK ABOUT THE JOB →