Ordova
The lessons have not stopped, and that is the finding. Everything else here taught me something and then finished; this one keeps changing, so it keeps teaching.
The claim everywhere right now is that AI replaces the engineer. What I keep finding is that it moves the engineer instead: from writing the code, to building the system that writes and checks it, to deciding whether to trust what comes out. That last decision is the part that doesn’t automate, and it’s still mine. It changes what the work is, day to day: I groom the tickets the moment a discovery lands, not because grooming is the done thing, but because the English is the code now and the Swift is what comes out of it. The system that does the rest is Ordova.
I can run this experiment because the risk is mine to absorb. Most businesses can’t gamble revenue to find out how much of the work AI can be left to do. I can run it on my own products and report what happens. If one fails, the lesson is the point.
The experiment is public from end to end, because proving it is the whole exercise.
Rob Nash Senior iOS Engineer
I wanted to know for myself whether AI is any use, rather than wait for the market to decide where I belong. I started out worried it would replace me. Having used it, I know it makes me better instead. What I still don’t know is how far that holds outside my own projects, so I keep testing and publishing what I find.
The work
Everything the studio has made, listed once under what it is. Where a name carries no state beside it, it is still being worked on.
The system behind the work
Ordova
The system the studio runs on: software agents that review the code, enforce the conventions, check the copy, and watch for drift. The last call, whether to trust what they produce, stays human.
ordova.async-digital.comIris
A Swift package that routes incoming URLs into typed SwiftUI navigation, so an app doesn’t have to hand-wire deep links. MIT, tagged from 1.0.0, listed on the Swift Package Index. The series is the evidence for it.
Deep links are plumbing right up until something automated starts firing them. Tests, Shortcuts and agents send URLs in bursts, mid-animation, into whatever state the app was left in, and none of the polite assumptions survive that.
adrelease
Releasing a Swift package and cascading the version bump through every internal package that depends on it, in one command.
I pin to the next minor, so only patch releases float in. Untested, but a risk I accept at that size. The tool assumed a caret, called the plan clean, then failed mid-cascade with the tags public. It blocks that now.
Learn Texas Hold’em
Teaching a complete beginner Texas Hold’em on the big screen. Simulated chips, no real money.
The Apple TV remote has four directions and a click. Every teaching idea I had needed a keyboard, so the remote is doing the design work now.
Audient shipped, on the Mac App Store
Now on the Mac App Store
Audient
A macOS app that uses on-device AI to transcribe and search the audio and video you give it.
audient.async-digital.com
What Audient taught me
Don’t let the agent run the project. Archive the decisions, keep the epics focused and clear, layer the code and stay critical about the architecture, and install hard gates.
Quill not released, built for the studio
On-device transcription from the command line. Point it at a file and it writes out the words, with no app and nothing uploaded. It runs here every day; the repository is private, so there is nothing to link to yet.
Local AI works. Transcription runs entirely on this machine, and I trust it enough to build on. I should still have built the command line first: doing it after Audient meant proving the same thing twice, in the harder order.
Mastering the AI Coworker published
Published · book
Mastering the AI Coworker
Principles for running an AI coworker in a one-person studio.
coworker.async-digital.comHow the book came about
I wrote the notes for myself, because I kept re-learning the same lessons about running an AI coworker. The book is those notes, ordered and argued for.
TimeZone Arc on hold
A glanceable dual-timezone clock, with a Home Screen widget and a watch complication. It is paused, not dropped. Ordova grew into a job of months, and the books are being written alongside it.
Shelving it was right and it still nags at me. A widget and a complication turned out to be two products, not two features.
FourBlocker abandoned, post mortem
Abandoned. Never released.
FourBlocker iOS
Turning work notes into four-blocker reports with on-device AI. I could not put a boundary around what the model would say.
- Built
- 13 February to 21 April 2026
- Code
- 9,300 lines of Swift, 2,400 of tests
- Languages
- English and Welsh, side by side
Last commit
What FourBlocker taught me
I could not honestly promise a user what the model would never say about their colleagues. That was the entire product, so it stopped.
Read the post mortem →Birthday Sleeps abandoned, post mortem
Abandoned. Never released.
Birthday Sleeps iOS
Counting the sleeps until the next birthday, on one screen. A finished v1, built for my daughter, who did not take to it.
- Built
- 13 June to 18 July 2026
- Code
- 5,600 lines of Swift, 2,300 of tests
- Languages
- English and Welsh, side by side
Last commit
What Birthday Sleeps taught me
Built for one user, aged seven, who wanted something else. Knowing what holds a child on a first screen is a designer’s specialism, and a brief cannot carry it.
Read the post mortem →The record
Working notes on running an AI coworker, and a case-study series still being written.