A test project I built to try the method
19mistakes in my own plan found before any code was written
23cases the tests never covered, found and run by the checker
2broken updates stopped before they went in
0caught by me
Waiting list open
Join
For people who build apps with AI
Built and tested by Burgess
Vibe-code your app on cheap models. Keep one frontier model in charge. Ship nothing on trust.
You build apps with AI. This is a tested way to catch the bugs you can't see, before your customers do. One strong AI manager, cheap builders and checkers, and checks that stop anything unproven.
Any model. Any seat. You choose.
Built and tested by Burgess
The problem
It worked in the demo.
Then it broke in real use, and you found out from a customer. The AI wrote it, nobody checked it, and you couldn't tell what to look for.
One strong AI manages. Everything else is checked.
One strong AI acts as project manager. It writes the plan, reads the results and decides what goes in. It never writes code. Cheaper models do the building, and a different cheap model checks every piece of work.
01 · MANAGER
Plan
The strong AI writes the plan and decides what goes in.
02 · BUILDER
Build
A cheaper model builds, after explaining its plan first.
03 · CHECKER
Check
A different cheap model names what the tests missed, then runs it.
04 · AFTER EVERY MERGE
Check the whole app
The checker reads the entire app. Anything it finds goes back to the builder. Repeat until nothing is found.
↺ Found something? The manager sends it back to the builder, the checker looks again, and it repeats until nothing is found.
STOP 1The builder explains its plan first, which is where it tells you when your own instructions are wrong.
STOP 2The checker lists what the tests missed, then runs those cases.
STOP 3Nothing goes in while a test is failing.
STOP 4After every merge the checker reads the whole app. Whatever it finds goes back to the builder, and the loop runs until nothing is found.
Nothing goes in unproven.
I've run it twice.
A real app, in one day
7updates built and merged
1,431→1,501tests, none skipped
6/7went in first time
4whole-app checks. The first three found problems with every test green. The fourth came back clean.
One of those problems would have told users their first step took 1,442 minutes. 1,486 tests were passing. Nothing was red.
Anyone can say "have an AI check it." The hard part is the system that makes it happen every time.
Four steps look simple. What makes them hold is the machinery underneath, and that's what you get.
Managerplans, audits, decides
Builderbuilds
Checkerchecks, finds what tests miss
Youwatch, and make the calls
01
A communication bus between the seats
The manager, builder and checker talk only through the bus. Nothing happens in a chat that nobody can see, and every handoff is on the record.
02
A written brief for every update
What to build, and what "done" means, before the builder starts.
03
A decision log
41 decisions written down in one day, each with its reason, so nothing lives in anyone's head.
04
A failure log
10 failures recorded. Each one becomes a rule, so the same mistake can't happen twice.
05
Proof before every merge
A clean copy of the app, tests run twice, then the code is broken on purpose to prove a test notices.
06
Hold, don't guess
When an AI hits a usage limit or an error, the manager stops and reports. It never swaps in a replacement quietly.
07
A fresh checker for every fix
The checker that gave the old verdict never grades its own fix. The manager also verifies every finding before acting on it.
08
A rulebook of 19 sections
Every rule is tied to the real defect that created it. Nothing is there for show.
A real send-back, straight off the bus
12:42Builder says it's ready. All tests pass.12:45Manager sends it back: real code had been shaped to fit old tests instead of fixing them.13:03Builder says it's ready again.13:25Checked, merged. Tests 1,452 → 1,462.Every test was green at 12:42. The manager read the change and caught it anyway.
What you get. And what you don't.
What you get
- The written method, with every rule tied to the mistake that created it
- A starter kit: drop in one file, answer two questions
- Templates for plans, handoffs and checks
- A checklist for the checker, and a final audit for the manager
- A guide to the tool shown in the video (swap in your own)
- A video: one project, empty folder to finished
What it isn't
- Not a tool or a model. You use the AI models you already pay for.
- Not "no bugs." It's "nothing goes in unproven."
- Not free of strong-model cost. You need one strong model as the manager, and you choose which one. Everything else can be cheap.
Who's behind this
I'm Burgess. I spent years finding faults for a living, in networks, in Windows and in security. Now I build apps with AI, and I wrote down how I stop them shipping bugs.
Waiting list
Get on the list. One email, when it's ready.
Tell me what would help you most. It decides what I build first.