Building AI‑First
Products.
I ship the tools I wish existed — for content, for developers, for the work of shipping itself.
BlackOps Center, VitalWall, and VoiceCommit are live experiments in what AI‑native software looks like in production — built and operated with the same patterns I apply to everything.
Front-end architect · 30+ years building at scale · shipping AI-first products
psst — try ⌘ A for Asteroids, ⌘ ⇧ L for Lunar Lander, or ⌘ ⇧ X for Missile Command
Get the Inside Track
Weekly insights from 30 years of building software — now focused on AI workflows and the systems we're building at BlackOps Center.
AI Development Tips
Real workflows that save hours
30 Years of Dev
Lessons from a long career shipping software
Founder Notes
Behind the scenes building BlackOps Center
No spam, ever. Unsubscribe with one click.
Applied AI in Production
These products are how I test and refine AI-driven development in real systems. Each one is built and operated with the same AI-driven patterns I apply to everything I build.
BlackOps Center
Agent-native publishing, driven over MCP
The agent-native content operating system. Exposes its whole surface over MCP, so the agent already holding your context can research, draft, publish, and read the analytics back.
VitalWall
Used by 500+ websites
Real-time website analytics and visitor tracking platform that boosts engagement through intelligent social proof.
VoiceCommit
Zero to GitHub in 60 seconds
Voice-first developer tool that turns spoken ideas into GitHub Issues, PRs, and updates. An experiment in removing friction between thinking and shipping.
Latest Articles
Renaissance Painters Who Lived to See Photoshop
Painting took roughly five hundred years to get from ground pigment to a brush tool on a screen. Web development did it in a couple of years, and those of us who learned it by hand got to see both sides.
Those of us who learned web development by hand are Renaissance painters who lived long enough to see computer paint programs. AI did that to web development in a couple of years, and it changes who gets to commission the work.
I did not want another writing tool
The first question should be what do you know, not what do you want to write.
Every AI writing tool opens with a blank box and asks what you want to write about. Then the model invents something, and it reads like it was written by someone who has never done the work. The gap worth closing is not writing. It is the hour between knowing something and having published it.
How I use a BlackOps brain to track my deploys
A brain is a set of markdown notes the agent keeps and reads back. I backfilled 34 deploys into one and it found a failed build I had no record of.
I asked BlackOps for a brain called Deployment Log, backfilled 34 deploys into it out of the build logs, and it caught a failed build I had never recorded plus a fix I had already made too narrowly.
Claude's Watermark Has a Shelf Life
It marks assistance, not authorship. And assistance is about to be on everything.
Anthropic now watermarks Claude's text output worldwide. The mark works. It will also stop meaning anything, because assistance is on its way to being universal and a signal present on everything distinguishes nothing.
Slop Is What Falls Out When Nobody's Steering
Medium won't buy an AI detector. They're right, and the standard they're describing is one most human writing has never cleared.
Medium sent me an email about AI detection and answered its own question. Here is what actually separates writing worth reading from slop, and why twenty rules and an eval gate still didn't catch the bad sentence in this post.
The Work Starts When the Thought Does
An autonomous SDLC where a note fires a Claude session, and the pull request is waiting when I get home.
Self-healing software survives its bugs without changing a line. What I run against my projects changes the source. Logging the defect is what fires the work, and most days the completion email is the entirety of my involvement.