hi, I'm Clint.
From Vision to Execution, I build products people ❤️
I was building predictive analytics products before it was cool. Full-stack engineer and cloud architect.

A caddie that
speaks first.
It reads the hole, the wind and your own game, then tells you the club and the target out loud, in the voice of the caddie you pick.
On the App Store now, starting with golfers where the season never ends. Everyone else, when yours starts.
iPhone · Apple Watch · Ray-Ban Meta (Android coming)
Hear a caddie · 21 of 56
Characters are parodies. Voices are synthetic.
7-day free trial, then from $9.99 a month.

latest →
9 min readApplied LLMs & AI engineering
Make Your LLM Write Like an Aircraft Manual. Then Lint It.
Make an LLM write like an aircraft manual with ASD-STE100, then enforce it in code: a clinic vocabulary, a linter, and doses the model never writes.
Read it →

Latest writing
All 111 articles →- LLMs, agents, evalsReview the Evidence, Not the Diff
- LLMs, agents, evalsYour Codebase Is the Biggest Prompt
- HL7, FHIR, MirthAI Browser Agents for Prior Authorization: API First, Portal Under Supervision
- HL7, FHIR, MirthLLMs Can Generate Clinical Quality Language. Don't Let Them Run It.
- Staff+, teams, debtIs Low-Code Dead? The Builder Is. The Governed Data Layer Isn't.
Where to start
pick the one that sounds like you, read them in order
You work in healthcare tech
You build with LLMs
Series
HL7 & Mirth from zero
Shipping LLMs in production
Code agents can be trusted with
React state, then and now