Ryan Ilano, AI-Native Design Engineer, New York.

Projects

Selected Works

Writing

Deep dives for the technical reader

The closest you'll get to Brave Origin for macOS without paying for it Brave sells Origin, a de-cluttered build, for $59.99. The same features switch off by managed policy on a normal install. One script, one sudo, ten lines I changed and why, and the two I got wrong first.
Your TV Is Spying on You Smart TVs use ACR to fingerprint what is on your screen and sell it. I caught my Hisense Google TV doing it 20 times in 15 idle minutes, with every privacy setting off.
Cheapshot: Everything to Save, Nothing to Trust A prescription label went up in a photo I uploaded for a cooking question. Cheapshot reads and redacts screenshots on your Mac, before anything reaches an API.
Your Rank Tracker Can't See 62% of What Gets Cited Only 11% of cited domains overlap between ChatGPT and Perplexity. Three of the five answer engines never look at Google's ranking, and Google's own two agree on citations only 14% of the time. What the AI agents actually read, what measurably works, and which best practice is already dead.
...Endtroducing A little background on me and my work, and a long-form version of my about page.
Resurrecting Subfolio: Bringing a Ten Year Old Tool Back with an LLM and Elbow Grease AREA 17's Subfolio CMS ran on PHP 5.6 EOL and was broken. Here's how I ported it to AstroJS and made it free to run on Cloudflare and GitHub Pages.
Local Self-hosted AI is now Useful with 16GB of VRAM Open weights got good, which is the only reason any of this plumbing is worth doing. Meticulous notes on setting up a Proxmox LXC with NVIDIA GPU passthrough, CUDA, and llama.cpp.
How I Run a Claude and DeepSeek Multi-Agent Dev Pipeline I learned agent orchestration by doing it by hand: Opus as architect and verifier, DeepSeek on the volume work, and a $20 Claude plan that goes a lot further than it should.

About

I design and build. No handoff, no translation layer: I take work from Figma to HTML/CSS to production. At Hearst that ran at scale for eleven years — one design system across 85 magazine sites and 60+ brands, on a network Hearst credits with 550M website visitors. I migrated and rebranded most of that portfolio onto it myself, and a brand redesign went from two months to two days, a 95% cut. Also an automated Apple News pipeline behind an estimated $10–20M/yr revenue line, and design lead on the accessibility program that reached 95%+ WCAG 2.1 AA (Axe Monitor), with 120+ properties audited program-wide. Today the same practice runs on AI products: coding agents on real work, routed across local models, DeepSeek, and frontier APIs by what each task actually needs. I call the split Gate and Wave. Opinionated about the system. Comfortable in a diff.

AI-Native Design Engineer — AI Products, Design Systems at Scale

I'm not against vibe code. I'm against vibe code in prod.

If that distinction matters to you, we should talk.

Get in Touch