68
Average daily patient visits, up from 25
Measured over the same period. A component of the growth, not the primary driver.
0
Inbound faxes handled by the front desk
The intake path runs without a person in the middle.
75
Peak daily visits
Measured over the same period as the 68 average.
I sat with the intake process as it actually ran — every fax opened by hand, identified, filed, forwarded. The cost was not any single fax. It was that the work was interrupt-driven and always first to slip.
Documents are classified the moment they arrive, filed to the right destination, and routed to the person who needs them. No human in the middle of the path.
The measure that mattered was not throughput. It was whether the front desk had stopped touching faxes at all — and what the reclaimed hours went into.
Every inbound fax was opened, identified, filed and forwarded by hand — constant, interrupt-driven work that was always the first thing to fall behind on a busy day.
Read moreEvery inbound fax was handled by hand. Front-desk staff opened each one, worked out what it was, filed it into the right folder, then emailed it on to whoever needed it.
The problem was never any individual fax — each one took a couple of minutes. The problem was that the work was constant and interrupt-driven. It arrived without warning, it could not be batched, and it competed with the patient standing at the desk. On a busy day it was the first thing to fall behind, and it fell behind precisely when the clinic could least afford it.
I built an automated intake path. Documents are classified on arrival — the system works out what each one is rather than a person doing it — then filed to the correct destination and routed to whoever actually needs to see it.
The design goal was to remove the person from the middle of the path entirely, not to make their part of it faster. A faster manual step is still an interruption.
The front desk stopped touching inbound faxes entirely, and moved that time to calling patients.
Over the same period the clinic went from 25 visits a day to 68 on average, peaking at 75. I won't tell you the automation caused that — it was a component of it, not the primary driver. But the staff hours it freed went straight into the work that grows a clinic.
If the answer you need isn't here, ask me directly.
No, and I'd be sceptical of anyone selling you that. AI is a force multiplier, not an employee replacement. The businesses that get real value from it are the ones that understood their own operations first — the technology amplifies whatever process you already have, including a bad one.
n8n for orchestration, Claude and OpenAI models for the reasoning layer, and whatever systems the business already lives in — EHRs, practice management, CRMs, Microsoft and Google's stacks. The goal is to fit the tools to the operation, not to move the operation onto a tool.
In the work you do hundreds of times a month without thinking about it. Billing, intake, routing, follow-up, reconciliation, reporting. It rarely pays off in the interesting, judgement-heavy work people assume it will — that's where you want your humans.
No. Most of the leverage I've seen is at mid-size operators — big enough that the repetitive work is genuinely expensive, small enough to change how they work without a committee.
By understanding how the business actually runs, which is usually not how the org chart says it runs. I map where the time and the handoffs are going before proposing anything. You cannot automate a process you haven't understood, and most failed AI projects are failures of that step, not of the technology.
Yes. Reach out through the form and pick 'Speaking' — it routes straight to me.