I lead AI engineering at OFX, where I build production agents that take on real operational work with humans still in the loop. Outside that, I build small agents for everyday problems and put them online. Here are a few of them.
An agent fleet that hunts loyalty points while you sleep. Tell it your programs once. It hunts overnight and sends a ranked morning brief of what is worth doing, and what it skipped, with reasons. Governed by design: it refuses, asks, and logs before it acts.
An AI agent security platform: intelligent monitoring for agents that take real actions.
A multi-agent system that works out exactly what is going on with your energy bill.
An agent-driven advisor for navigating compliance questions.
I am drawn to agents that do the useful, time-costly work people never get around to. The harder and more interesting part is doing it responsibly: knowing when to act, when to ask, and when to stay out of the way.