Radiology Specialist · Chief Innovation Officer · Built CBCTScope
I build AIwhere being wrongisn’t an option:medicine.
Most AI advice has nothing at stake. I read medical images every day as an oral and maxillofacial radiologist, and I build, evaluate, and train the imaging AI I work with. These essays keep that bar: what a model did on a real case, what it did not, and how to build alone without fooling yourself.
100,000+ reports signedCBCTScope shipped, open sourcewhat I’m building →
// Latest writing
One-Person Startup5 minAgent-native imaging: why I gave my CBCT viewer to the agents
Why I built CBCTScope, an open-source local-first CBCT viewer with native AI-agent control over MCP, and why the agent gets navigation verbs but never a verb that returns a finding.
One-Person Startup12 minYour AI Account Knows How You Think
Your AI chat account stores how you think—not just what you said. Learn the 4-Layer Defence Framework to protect against hackers and providers.
One-Person Startup10 minThe 2-Tool Rule
Too many AI tools create fragile workflows and decision fatigue. Use the 2-Tool Rule to restore focus, improve prompt reliability, and build long-term skills that survive AI model changes.
One-Person Startup11 minModel Updates Break Things. Stabilize First.
Discover why AI model updates break production workflows and learn the stabilization framework that prevents these disruptions. Keep your AI systems running smoothly through updates.
One-Person Startup9 minPrompts Don't Travel. Translate Them.
Learn why copying prompts between different AI models fails and discover the 3-step translation framework that makes your prompts work across any AI system.
// Browse by series
// Agent-native instruments, open source
Newsletter
Get the essays as they’re written.
New pieces land in subscribers’ inboxes first. Free, no noise.