● Urgent-care operator · AI-agent engineer
A growing share of my urgent-care company's operations runs on a fleet of AI agents I built — and I write down how it actually works so you can use it too.
Intake, scheduling, charting, billing — the whole day, run by agents, with a human on the calls that matter.
How I run it → You build with AIAgent harness, self-verification, recovery, the failures nobody screenshots — written to lift straight into your own agents.
Read the field notes →
Before an agent writes anything, it has to prove it's in a disposable copy of the repo and not my real one. The obvious command for that returns a confident answer to a different question.
A common trap in automated content and document pipelines: you correct the underlying data or code, but the person on the other end still sees the old versio…
Filing a ticket creates the appearance of progress while nothing is actually owned, scheduled, or moving.
An LLM's attention is cheap and a human's is scarce. Spend the cheap one to protect the scarce one.
A bilingual classical-music learning product that guides people through pieces with stories, context, and things to listen for — not intimidating analysis or assumed expertise.
A single web platform that runs a clinic's whole day — check-in, a live provider queue, lightweight charting, telehealth, staff messaging, and billing — instead of a dozen disconnected legacy tools.
The sole captain-facing product surface for dispatching agent work: Firstmate routes goals through persistent secondmates, keeps subordinate workers internal, and watches sessions for trouble — rate limits, context exhaustion, dead sessions — so work can recover automatically.
Building agent systems inside a real business — or running a clinic and wondering what this could look like for you? That's exactly the conversation I want to have. No form, no funnel.
