AI agents for knowledge work · platforms · South Lake Tahoe
I help teams trust AI agents with real work.
I've spent ten years building the platforms engineering teams run on. At Khan Academy I drove AI adoption across the organization, building the tools and teaching people to use them well. Now I do the same for other teams, especially ones whose work does some good.
Give agents access to your tools, integrations and data without handing them the keys. They only get the access a task needs, and a person approves the decisions that matter.
I've worked extensively with sensitive student data, so confidentiality is where I start.
Repeatable tests of how agents and models actually perform, with cost tracked per model. I bring spend down by making usage more efficient, not by rationing it.
Agents that check work before anyone relies on it, whether that's a contract, a research memo, a report or code. Findings get verified before they reach a person, follow-ups only look at what changed, and the people using it shape how it works.
Tools only pay off if people use them. I teach teams, engineers and non-engineers alike, to work well with AI, set practical best practices, and keep the tools simple enough that they stick.
Build, test and deployment pipelines and cloud platforms that are quick, cheap to run and easy for your team to own after I'm gone.
egg is my side project, still in development. Agent teams turn an issue into reviewed pull requests while a person makes every decision that matters. Agents hold no credentials, there's no merge button for them to press, and every review has to cite real evidence.
Ten years at Khan Academy, Asana, Rally Health, Intuit and Capital One, across education, healthcare and finance. The details are in my resume.
I'm open to full-time and part-time roles and to consulting, especially with mission-driven teams. If you're near Tahoe or Truckee, coffee's on me.