Writing
Field notes, essays, case studies and process posts, on 4 shelves. Pick a shelf or type a word to narrow it down.
Case Studies (8)
Real brand, content and product work, with the numbers.
The 1866 Studio: An AI Operating System for Small Business
Huntington announced The 1866 Studio, an AI-powered small business operating system built with Google Cloud. I designed the experience.
2 min read
08-19
Huntington: Launching a National Golf Platform
Huntington built a golf platform around World No. 1 Scottie Scheffler. Idea to launch in Sitecore, shipped in stages because the rights cleared in stages.
3 min read
08-18
Designing Mantium: Enterprise AI Chat UX (Case Study)
I led UX design for Mantium, an enterprise GenAI platform: onboarding, secure chat, and a no-code app builder. First deploy went from 2+ hours to under 30 min.
3 min read
08-18
Cardinal Health: Redesigning an Enterprise Dashboard
Modernizing the Order Express dashboard pharmacy customers rely on, inside the brand, CMS, and compliance constraints of a regulated enterprise.
2 min read
08-18
Kahle Nutrition & Chiropractic: Website Design Case Study
Kahle Nutrition & Chiropractic had no website. Now patients can find, trust, and book: strategy, design, launch, and the technical plumbing.
2 min read
08-18
Arloa: How I Designed the Product, Brand, and Launch
How Arloa was designed. I led product design, brand, and go-to-market for a generative AI platform that helps parents manage IEPs and school communication.
2 min read
06-12
Designing Enterprise AI for Non-Technical Users
What Mantium taught me about making model capability legible to people who will never read a prompt guide.
3 min read
06-12
Tripling Content Output With a Four-Person Team
The Claude Code content pipeline behind Arloa. 4 to 12+ pieces a month without adding headcount, and without losing the brand.
3 min read
Creative Direction With AI (3)
Taste, direction and the rules that keep AI output on brand.
Teach the AI Your Taste
How to have AI think like a designer, lock in a vision, and hold it accountable to it. A free skill pack and the blueprint behind it.
5 min read
08-27
AI Proposes; A Defined Checkpoint Decides
The one rule under everything I build with AI. Generation is cheap, judgment is the product, and the judgment has to be deterministic.
7 min read
08-20
The Only Designer, and I Shipped the Code Too
Being the only designer on a four-person team, collaborating on the codebase in Claude Code and GitHub, off a brand system built in Figma.
2 min read
Building Agent Systems (7)
How the operating system works: files, gates, agents and the claims they are held to.
Files Move. Platforms Don't.
I shipped a complete product vision as a folder of files any AI can build from. On provider-agnostic systems, and why the file is the interface that survives.
5 min read
07-31
One Token, Twenty-Seven Dashboards
I picked a typeface for a website and ended up re-typesetting an operating system, including the contrast failure I couldn't see by eye.
4 min read
07-30
A Claim Ledger for the Person You Market
Every claim I make about my own work now traces to a dated source file, or it doesn't ship. On building a claim ledger for the person you market: yourself.
3 min read
07-30
Under the Hood: This Site
This site is generated from markdown by the same system it describes. The build script, the content rules, and why there's no CMS.
2 min read
06-12
The End of the Second Brain
Knowledge management was never the goal. Why I'm building an agentic operating system instead of another notes app.
6 min read
06-12
Your Files Are Dead. Here's What Comes Next
Files made sense when humans were the only readers. On moving from documents you organize to context a system can act on.
5 min read
06-12
The Agent Deployer: A New Role Emerges
Between the engineer and the end user there's a new job: the person who deploys, governs, and owns agents in production.
4 min read
Side Projects (5)
Experiments built on my own time to see what agents can do.
A Betting Agent on Live Data
A side project to see if an AI-built agent can run on live sports data every day without me. The pipeline works. The edge does not, yet. So it's open source.
5 min read
07-30
I Taught My Investment Agent to Refuse
The most important function in my portfolio agent throws an error when output starts sounding like advice. Designing the boundary before the feature.
3 min read
07-30
Under the Hood: The Sideline Board
A game-day sideline board built as data plus a renderer, and how the same content-in-files pattern behind DavidOS handles live cards.
2 min read
07-30
Under the Hood: The Patch Archive
Rebuilding a military patch archive with an agent pipeline: research, redraws, and a render script that turns markdown records into a browsable site.
3 min read
06-12
A Trading Agent With a Human Approval Loop
Building a Robinhood agent that proposes and never executes: prompts, guardrails, and why the approval loop is the product.
9 min read
Nothing matches that. Clear the box or pick another shelf.