iOS tech lead · building with AI agents
I lead iOS development at a bank and build products with coding agents that work from specs and tests. This is where I write down what works, what didn't, and why.
A dinosaur learning game for children aged 4 to 7.
React · TypeScript
An offline iPhone app that reads your notes aloud.
SwiftUI · Swift Testing
$ agister run review
resolve ✓ 3 definitions
admit ✓ budget 1.20 USD
record runs/7f2c/
A runner for AI-agent work defined in settings files.
Go
Learning programs your own agent can work on.
Node.js · SQLite
Agonara can grade a student's open answer with any model behind an OpenAI-compatible endpoint. The model grades per criterion, its output is validated before a student sees it, and the work runs as a leased, retried, budgeted job.
In Agonara, model suggestions and curator drafts never become program content by themselves, accepted content is kept as revisions, and a student's answers are pinned to the revision they answered. How the modules keep their own data apart.
Agonara is a bring-your-own-agent environment for learning programs. A curator builds a program from sources, students follow it and prove they understand, and the agent you already use does the drafting, quizzing and grading. What it is and why only a person accepts content.
The code review that ships with Agister runs several lenses in parallel, one of them a writer–critic debate in a bounded repeat, before a judge merges the findings. How it is composed from settings.
Every Agister run leaves a folder with the exact definitions by digest, inputs, permission plan, events and patches. Why the record matters more than the terminal output when agents do the work.
Agister is a Go command-line runner for AI-agent work defined in settings files — agents, processes and workflows — with a record of every run. What it is and why I built it.
Skipping by sentence and resuming where you stopped sound trivial. In FolioTell they meant mapping UTF-16 offsets from the speech engine back to sentences in the original text.
AVSpeechSynthesizer is asynchronous and full of late callbacks. How FolioTell keeps playback correct with pure reducers, effect handlers and utterance tokens.