How we design, build and ship software with AI agents.
Keeping AI usage costs visible inside a product
Gripz meters AI usage in plain view and alerts the team before it reaches the limit. Here is how to design and build a usage meter like it.
Read articleWhy every product gets its own design system
Ten products, ten design systems. We set up the tokens and components before the first screen, so agent-written code has rules to follow.
Nov 2, 2026How AI agents and engineers split the work
Agents write code and tests at agent speed. A person makes the decisions and reviews every change before it merges or ships.
Nov 2, 2026The decision log we keep on every project
Scope, decisions and trade-offs are written down beside the working product, so anyone can see why it works the way it does.
Nov 2, 2026Shipping iOS apps from Windows with Expo and EAS
Our Expo apps build in the cloud through EAS, so a Windows machine can take an app from code to TestFlight without Xcode.
Nov 2, 2026Checking UI at five widths before every release
Before a release we check the interface at 320, 390, 768, 1024 and 1440 px. Here is a headless browser setup that captures every width.
Nov 2, 2026Product films as code: ten films from HTML
We made ten 10-second product films, one per product, as HTML pages rendered to video. Building them in code keeps each film on its design system.
Nov 2, 2026No build notes in this topic yet.
Build it
with
clarity.
Tell us what you are building and where it stands today. We will reply with questions and a first plan. Write to [email protected].
- ReRezanCo-founder
- RaRanaCo-founder