Case studies

Verifiable builds. Real numbers. Public source.

These are systems I designed and shipped myself — one that measures whether AI agents are safe to trust in regulated work, and one that turns a real problem into a live product in a weekend. Both are open to inspect: read the code, open the demo, check the numbers.

On client work

Client engagement write-ups get added here as clients opt in.

The two studies above are my own builds — the clearest way to show the work when a firm is young and client engagements are still under NDA. As Assessments and Builds wrap and clients agree to share, named and anonymized write-ups will join them: starting-state diagnosis, the tier chosen, the system shipped, and the measured result — including honest trade-offs and anything that was out of scope.

Want to see this applied to your workflows?

Book the AI Readiness Assessment. If I can’t find $5K/month in recoverable time, I refund it.