My Agent Kept Signing Its Mail With Someone Else's Return Address
A tmux pane-id bug taught me to pin agent identity to my own process, not to whatever the system says is active.
● 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 →
A tmux pane-id bug taught me to pin agent identity to my own process, not to whatever the system says is active.
When you build automation that infers connections from activity logs or transcripts, resist the urge to write its conclusions directly into your source of tr…
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 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 orchestration layer that launches agent sessions, watches them for trouble — rate limits, context exhaustion, dead sessions — and recovers them automatically, using deterministic scanning instead of fragile notifications.
A kiosk and mobile intake flow where patients check themselves in — confirm demographics and insurance, sign policies, answer pre-visit questions — and drop straight into the live clinic queue.
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.