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
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. The system that does the rest is Ordova.
I can run this experiment because the risk is mine to absorb. A business can’t gamble its revenue to find out whether hands-off AI works. I can, on my own products, and report what actually happens. If one fails, the lesson is the point.
The products below are real. The findings are in the notes and case studies. All of it is public, because proving it is the whole exercise.
Projects
How we work
Case studies
Notes
-
Notes on coordinating AI agent swarms
An inventory of missing primitives in current agent-swarm runtimes, and the disciplines that fill the gap.
Read note
-
Your rules should travel with you
The rules built up working with an AI assistant are professional capital. They belong to the studio, not locked inside a vendor's product.
Read note
Open source
I release some of the code beneath these products as open source libraries. The first is Iris, the race-safe, state-aware deep-linking layer from the case studies, MIT licensed and public on GitHub.