Genacy Labs genacy.co ↗ App · Coming soon

How we build · Field notes from the build of Genacy

One stubborn human. A lot of AI.

Genacy was built by one person using AI models as the engineering team. This is the first-person account of how that actually went: the month with no code, the day the documentation started lying, the bug that hid behind green tests, and the afternoon a tool reported success while writing nothing at all.

501k
bytes of app.js by the end
494+
tests, grown from zero
11
sub-decisions to rename one word
418,970
the byte count that wouldn't budge
1
tool that quietly lied
The idea at a glance

A loop of decisions, building and evidence.

The founder sets the direction. AI does the engineering. Checks feed the next session.

  1. 01

    Decide

    Agree the workflows and constraints before writing code.

  2. 02

    Build

    Work in bounded sessions with clear handovers.

  3. 03

    Check

    Review structure, behaviour, content and the real browser.

  4. 04

    Learn & repeat

    Carry failures and lessons into the next session.

01The three acts

Twelve days that decided how everything since has been built.

Read them in order, or start with whichever sounds most like your week.

02The rules

Four rules survived all twenty-five sessions.

Everything else was negotiable. These were not, and they are why one person can move this fast without breaking things quietly.

01 · Context
Maintain what the AI reads.

It knows only what you put in front of it. The documents describing the project drift away from the project unless you force them back together, every session.

02 · Checking
Four levels, every time.

Does it parse. Does it behave. Is anything lost. And what does a real browser actually show. None of them replaces the others — we learned that one twice.

03 · Tools
A success message is a claim.

Verify the result yourself: the bytes, the render, the count. One tool reported success four times while writing nothing at all.

04 · Discipline
Write the rule down.

Every lesson becomes a rule the next session has to follow. A method you keep in your head is a method you lose when you are tired.

03Set up first

Take the time to set your environment up properly.

This is the advice nobody wants to hear and everybody needs. Before the interesting work starts, build the scaffolding: the house rules the AI reads at the start of every session, the skills it can call on, the trackers that say what is done, a lessons-learnt document that grows, test cases generated rather than hand-written, and permissions set so the tools can do their job without being able to do damage.

It feels like a day lost. It is the difference between an AI that compounds your work and one that quietly undoes it while sounding pleased with itself.

House rules

A file the AI reads every session: how we work, what is banned, what to do when unsure.

Trackers

One place that answers "where are we up to", generated from the plan rather than from memory.

Lessons learnt

Every mistake written up as a rule, carried forward into the next session.

Tests and permissions

Test cases generated automatically; tool permissions scoped so nothing can be quietly destroyed.

The whole method in one line

Decide first. Check four ways. Write every lesson down as a rule.

That is how a working platform got built for under A$3,000 by one person. The Technology page shows what it produced; the roadmap shows what is next.

Coming soon · First 2,000 trial users only

Would you like to join the beta trial?

Help shape Genacy and keep the early-member benefit for life.

Join the beta trial
3 monthsCompletely free
50% offStated prices, every month after that. For life.