Ryan Brady, marketing engineer
A marketer who builds the software around the work. Personal home for my bio, resume, writing, builds, and the tools I use every day.
Meet Ryan
Marketing engineer building AI into the daily workflow.
Most days now I'm shipping AI agents, custom tools, and automation systems — the kind that take a workflow that ate hours and turn it into something that runs itself. A career inside enterprise search and growth sits underneath it all. Based on Long Island, NY.
This site is the personal home for everything I've built, written, and learned along the way.
Recent
What I've been working on
- A GTM system for a company of oneAI ops / GTM
My consulting practice needed a CRM, a project tracker, and an ops brain — so the client was me. The operator is one person and the source of truth is a folder of YAML files. So the pipeline, the engagements, and every Claude Code session on the machine render into one live dashboard. There's a fully synthetic interactive demo you can click through.
- A fully automated houseHome automation
The cats' litter box, every light, every fan, the robot vacuum, the thermostat — it all runs on a mesh of home APIs and a few custom scripts. I haven't flipped a physical light switch in a while.
- Rare Coin ScannerComputer vision
My grandfather left me a stack of coin albums I'd never gone through — too many of them, and I didn't know enough to know what mattered. AI made it feasible to finally look. The pipeline scans an album page, identifies each coin in its holder, validates against the slot label, and flags anything worth a closer look.
- I Was My Own First Client: A GTM System for a Company of Onegtm-engineering
Digital Braid needed a CRM, a project tracker, and an ops dashboard. Instead of buying three SaaS tools, I built one system that reads the files I already keep — and published a fully synthetic, clickable demo of it. Here's the architecture, the three rules under it, and the sanitization gate that earned its keep on day one.
- Building UI with AI: the component vocabulary that makes it workui
Every UI component you ship with AI tools answers to two audiences: the model you're using to build it, and the AI crawler that has to read it. Most teams work with neither in mind. Here's the vocabulary that makes both easier.
- Context Engineering: Why the Context You Give Shapes AI Output More Than the Promptai-automation
Most teams trying to improve their AI output are tweaking prompt wording. That is the wrong lever. Here is why context, not prompt craft, is the thing that actually moves quality, and how to build a context library that does it right.