AI writes the code. We decide what to build and prove it works.
AI writes the code in our projects. Most of the time goes into the two steps around it: deciding exactly what to build, and proving that the finished software works. Our five phases are planned around those two steps.
Specify
We write a detailed description of what the software must do, detailed enough for AI to write the code from it. It is longer than a normal requirements document. Every later step depends on it, so it gets the most time.
Build
AI writes the code from that description, in small pieces you can open and try on the same day. This step is quick, so it no longer sets the length of the project.
Check
Every change must pass a set of automated tests, written from the description, before it is added to your code. Code that no test has checked costs more to fix later than it saved when it was written.
Prepare for launch
We test load, security, monitoring, and what happens when parts of the system fail. AI usually gets the normal use of the software right on the first try and often misses the unusual cases, so we add those here.
Run
We keep supporting the software after release. A fast first version has little value if it stops working in its second week in production.
Our rules
The rules that decide how every project runs.
The description decides the result
When AI writes the code, the quality of the software depends on how clear and complete the instructions are.
Test everything
AI writes every line, and a large set of automated tests must show that it does what the description says before it is released.
You see the work as it happens
You can open each new piece of work on the day it is finished, instead of waiting for a demo at the end of the month.
The saving is yours
We use AI to go faster instead of hiring more engineers. That saving lowers your price.