Writing
Thoughts on building software that lasts, AI that actually helps, and lessons from 30 years of production code.
2025
DecisionForge Postmortem: What Failed, What Shipped, What Stayed
A candid look at the multi-LLM debate product—dead ends, fixes, and the pieces that actually delivered value.
The Documentation Nobody Sees: Audit Reports, Technical Specs, and Proof
Building credibility assets - the audit reports, specs, and documentation that prove your claims are real.
AI Debate Engine: How It Works Without Leaking Secrets
A high-level look at the multi-model debate engine—roles, routing, and guardrails—without sensitive prompts.
Rebuilding My Personal Brand at 30 Years In
The uncomfortable process of repositioning after decades of building systems instead of reputation.
I'm Not 'Just a Healthcare Person' (And Why That Label Cost Me Millions)
Breaking out of vertical pigeonholing - how domain expertise becomes a trap and what transfers across industries.