Your Recent Service: What AI Gets Right That Healthcare Gets Wrong
What my MS infusion center texted me after pumping $12,000 of biologic into my veins
I have MS. I do not talk about it constantly, but it is there, and it shapes how I think about a lot of things, including technology, medicine, and the gap between what is possible and what actually gets built.
Here is the good news about MS in 2026: thanks to modern medicine, a degenerative neural disorder is often not so degenerative anymore, as long as you take your meds. The meds, however, are not aspirin. They are sophisticated biological agents administered intravenously at something called an infusion center.
Despite sounding like something you would find at a boutique hotel bar, an infusion center is actually a room full of comfortable chairs where nurses hook people up to IV bags of expensive drugs. My first visit was last week. Most of the other patients were regulars, showing up at carefully scheduled intervals for treatments targeting MS, rheumatoid arthritis, Crohn's, rare genetic disorders, and other conditions that require ongoing, precise medical management. These are not casual patients. These are people whose lives, in some meaningful sense, depend on showing up. Several were already using walkers. One arrived in a wheelchair. These appointments exist to prevent exactly that.
So you can imagine my reaction when I got home and found this text waiting for me:
“Hi Michael, Thank you for your recent service with Paragon at Austin 720 West 34th St.! Your opinion counts! Please take the time to complete a one question survey at the following link...”
My recent service.
I did not get my oil changed.
Neither did any of those other people in those chairs.
A phrase that generic is not just bad marketing copy. It reflects something bigger and worse: institutional decontextualization. The system knew perfectly well where I had been, why I was there, what drug I had received, and when I needed to come back. Yet somehow it spoke as if I had stopped in for a tire rotation.
A long time ago, back when “AI” meant expert systems and the iPhone did not exist, I built something for exactly this problem and filed it as a patent. Deliberately. I wanted it in the public record as prior art so nobody could lock it up and so anyone who wanted to build something like it could do so freely.
The idea was simple: healthcare providers already know who you are, what condition you have, what drug you were just given, and when you need to come back. Why should the follow-up communication reflect none of that?
The technology to do this crudely existed in 2002. It exists with remarkable sophistication today. So I did what any curious person with an LLM handy would do. I asked Claude to rewrite that text message given the actual clinical context of an MS infusion. Here is what it came up with:
“Hi Michael, we hope your first Briumvi infusion went smoothly. For the next 24 to 48 hours, watch for headaches, fatigue, or mild fever. These are common after a first infusion and usually resolve quickly. Anything more serious, like difficulty breathing or chest tightness, call us immediately at [number]. Your next infusion is typically scheduled two weeks from today. We’ll reach out to confirm, or click here to add it to your calendar now. How are you feeling?”
That took seconds to generate. It is personalized to the actual drug administered. It provides clinically relevant information. It is warm without being saccharine. It offers a concrete next step. And it asks a human question at the end.
No new data was required. The infusion center already had everything it needed: my name, my diagnosis, the exact drug I had just received, and my next appointment date. I knew where it was; I don’t go infusion-center hopping on the same day. The LLM simply connected the dots the way any thoughtful nurse would, if every nurse had infinite time and a perfect memory.
I am not here to predict jobs armageddon. I find those pronouncements mostly theatrical.
But this is different. This is obvious.
What I just described does not merely improve a patient message. It eliminates the need for communications that strip away context, flatten the patient into a transaction, and then wonder why healthcare feels alienating. It closes part of the gap between clinical excellence and patient experience, a gap most healthcare systems seem to treat as a routine cost of doing business.
And here is the thing: it is better for everyone. Better for patients, who get information that is actually useful. Better for providers, who build trust and reduce anxiety calls. Better for the business, because a patient who knows what to expect after an infusion is less likely to panic, less likely to miss the next appointment, and more likely to stay in the system.
Like it or not, that is the future. Not because it is inevitable in some grand technological sense. Because it is simply better, cheaper, and, though generated by a machine, more human than what is being sent now.
Your recent service.
Honestly.