Projects & systems

This app classifies email across all your connected accounts (iCloud, Gmail, Yahoo, work) entirely on your Mac — nothing is sent to a cloud. You define folders in plain English, and it files mail accordingly, learning from how you actually sort things over time. A companion iPhone app lets you approve or reject decisions and watch it run live. It's a product where the model is just one component — the privacy architecture and the decision logic are the real engineering. Under the hood: Swift, Apple's on-device Foundation Models by default (or open-weight models you run locally), with multi-account support.

• Zero email content leaves the machine — local models only
• 30,000+ of my own emails classified across multiple accounts
• Folders defined in plain English, and it learns from your corrections
• Companion iPhone app: approve/reject and live status, with no on-phone inference

This is a notes app where no plaintext content ever touches disk. Each note is encrypted with its own key, and that key is wrapped to a hardware security chip on the device — so a copy of the file is useless without it. I implement the handwriting shape recognition from first principles, tuned to refuse rather than guess at ambiguous strokes. It's a project about doing cryptography and hard algorithms correctly, with an adversarial review pass that caught a real security flaw before it could ship. Under the hood: Swift 6, zero third-party dependencies, 6,400 lines of app code backed by 295 automated tests.

• No plaintext note content ever reaches disk
• Per-note encryption keys wrapped to the device's Secure Enclave
• Adversarial crypto reviews caught a real error oracle before it could ship
• Hand-drawn shape recognition built from first principles — refuses to guess