The AI-native medical billing operation
Voice agents that call payers, a denial agent over a 4.7M-row knowledge base, and an RCM core, one operation rebuilt AI-first.
Founder, operator, systems builder
I build companies that run on AI.
A production fleet of autonomous agents runs four businesses, in regulated industries, around the clock. Not a demo. A running system you could audit.
Operating · the core56 live nodes · 6 active today
Proof of operation
Most founders describe their work. This is the telemetry of mine.
Live from one always-on workstation. Every number traces to a command output.
ARCHIVEone workstation
as of 2026-07-020
services running
0
scheduled timers
0
agents in fleet
0
commits
0
hourly snapshots
0d
days uptime
Four industries, one operator
I hold equity in four businesses and run them with a fleet I built.
Selected work
Systems that do real work, not demos that generate content.
A self-improving training methodology
Agents that diagnose their own failures and promote only statistically defensible wins, overnight, for the cost of electricity.
Frontier models on a 7.7-pound box
Hand-written C and Metal engines that run 397B and 671B open-source models on consumer Apple Silicon. A research paper to match.
Validatable pharma-compliance automation
57 minutes of manual closeout work reduced to 3, built to pass a 21 CFR Part 11 audit, with a local model so data never leaves the building.
Writing
Two minds, one mission.
Latest signal · I don’t hire ‘AI people’ first anymore.
Speaking
I do not pitch with slides. I pitch with telemetry.
Talks on production multi-agent systems, AI in regulated industries, and building a company that runs on AI, backed by a real operation you can verify.
Topics + booking →Newsletter
Field notes from building and operating AI in production. No hype.