SVP Software Engineering at WellSky, leading nearly 400 engineers. I write about AI-augmented development, software leadership, and building things that matter, backed by 35 years of experience.
AI-powered development combined with 35 years of enterprise expertise.
I build complete applications using Claude Code, Anthropic's AI-powered development environment. This isn't just autocomplete. It's an AI partner that understands architecture, writes tests, and delivers production-ready code.
Combined with GitHub Copilot and 35 years of hands-on experience, I deliver solutions in days that used to take weeks. Every AI-generated line is reviewed, tested, and validated by human expertise.
AI-augmented development dramatically accelerates delivery
Anthropic's AI builds entire features with context awareness
35 years of experience validates every solution
AI writes comprehensive tests for reliable code
Real solutions that delivered real results for clients across diverse industries.
The intelligence layer for E-Rate sales. eRateIQ scores every Form 470 the moment it is filed, surfaces the renewals competitors miss, and tracks the USAC changes that open the next deal. Smarter leads, faster wins.
Read Case Study
A private, local-first health platform for navigating a serious diagnosis. Anchor pulls records, labs, medications, and treatment research into one place and separates signal from noise.
Read Case Study
A passwordless web app that keeps an extended family connected: a shared directory of birthdays and addresses, an auto-built family tree, and daily reminders so nobody misses a milestone.
Read Case StudyInsights on AI, software development, and technology strategy.
For eleven days my dashboard reported a broken sitemap on a site whose sitemap was perfectly fine. Cloudflare was challenging my build agent while waving Googlebot straight through. The web is growing a guest list, the free-tier defaults change on September 15, and most internal tooling is on the wrong side of the line.
Eight days after I argued that picking a single best model is the wrong game, Anthropic shipped Claude Opus 5: near-Fable-5 intelligence at half the price, at the same cost as the model it replaces, with a dial that trades effort for money. It did not retire routing. It moved the router inside the model.
A dozen models dropped in about two weeks: Sonnet 5, the GPT-5.6 family, Grok 4.5, Kimi K3, GLM 5.2. If you are still trying to pick the single best one, you are playing the wrong game. The wave did not crown a winner. It retired the question, and made routing the skill that matters.
Find me on LinkedIn
