Operating Notes
Company-Building Under Real Constraints
Decisions about customer concentration, automation, services, enterprise risk, and pivots.
I build software for workflows where failure has real consequences.
I lead Routespring, where I’m building LLM and voice agents for exception-heavy airline operations.
My work sits at the customer-to-product boundary: understand the operating problem, design the system, get it into production, and turn repeated implementation work into product.
Before Routespring, I co-founded GlobalLogic, hCentive, and Pine Labs, serving as CTO at each.
Current work
TraceGuard is a research project on checking an agent’s work against the systems it was meant to change. The prototype uses synthetic travel workflows and injected failures.
Deterministic Offload replays an agent’s logged decisions against the operator’s own corrections to find the calls a model never needed. In 631 of my message-routing decisions, six written rules represented my policy better than the model did. Code makes those calls now, and the method is in a short paper: When Can You Delete an LLM Call? (PDF).
PillWatch is a small computer-vision system I built with four high school students. It forced us to think carefully about small datasets and system-level error.
Writing on AI
-
The LLM call you can delete
631 replayed decisions, six written rules, zero disagreements. The model I was paying to route my email lost to the policy file it was reading.
-
Task managers are the wrong abstraction for AI agents
A task says what to do. An obligation also records why it exists, who owns it, when it is ready, what action is allowed, and what proves it finished.
-
PillWatch: 99 percent accurate, wrong every fifth box
Four high schoolers, a $60 Raspberry Pi, and the compounding math that turns 99 percent per cell into an error every fifth box.
-
1,029 cells: what small, honest data teaches about AI
The PillWatch team labels its own data, splits it by photograph, and hunts its rare cases deliberately. That discipline taught more than model tuning did.
Routespring
AI agents for exception-heavy airline operations.
Production agents need clear permissions, checks against source systems, and an explicit handoff to a person. We trust completion only when those systems contain the expected result.
Before Routespring
I co-founded Pine Labs, GlobalLogic, and hCentive, serving as CTO at each, and later led Gallop.ai. The company history has the dates, roles, and sources.
Up Robotics
Co-founder and advisor
A hands-on robotics and engineering program for young students. I help with strategy, technology, and the occasional problem that needs more adults than children.
Off Duty
Away from work: robotics, over-built home infrastructure, and ranked lists of films and shows I keep thinking about.
Contact
For AI, airline, travel, founder, or Up Robotics conversations, use the contact page.