AI for Vets Writes Notes Faster. It Never Notices Who Stopped Coming

A kelpie named Banjo was due for his C5 booster last November.

The reminder SMS went out on time. His owner meant to ring back after payday, then school holidays happened, and nothing did. Nobody at the clinic noticed, because nobody is paid to notice. Fourteen months later Banjo is on a table across town, at a practice that opened last year.

That same week, the AI scribe you trialled wrote up every consult before the patient left the room. Your head vet went home forty minutes earlier. A genuine win, on appointments that were already booked and paid for.

That is the shape of AI for vets as it is sold today. Nearly all of it points at the consult room: scribes that turn the conversation into clinical notes, imaging tools that flag what a tired eye might miss. I build these systems for Australian businesses, so let me say the unpopular half out loud. Your clinic does not bleed inside the consult room. It bleeds in the gap between visits, where nobody is watching.

What AI for vets gets right

Give the scribes their due first, because the case for them is real.

Clinical notes have eaten veterinary evenings for as long as the profession has existed. A scribe that drafts the record before you have washed your hands gives a vet back real hours, and in a market where every clinic is short of vets, hours are the scarcest thing you own. If a scribe keeps one good vet from burning out, it has paid for itself.

Two things are true about it anyway. The scribe only works on consults that happen, and the record stays your responsibility, so you read it before you sign it. You have bought speed on work you were already going to be paid for.

The half of AI for vets nobody demos

Now look at the other side of the same clinic.

The vaccination that lapsed four months ago. The dental you recommended in autumn that was never booked. The puppy that came in twice and vanished. The phone that rang out at 5:50pm while both nurses were holding a fractious cat.

That work was always mechanical. It never had anyone spare, so it slipped, and it kept slipping, because none of it feels urgent until the appointment book has more gaps than it did last winter.

A scribe saves minutes on the patients in front of you. The patients who stopped coming take whole years of revenue with them.

Your recall list is the asset nobody watches

Every patient file in your practice software decays from the day it goes quiet. Owners move suburbs, pets age, a competitor opens with a shinier waiting room. A file nobody has contacted in two years is closer to a memory than a patient, and you paid real money to create it.

Your software can already print the overdue list. That was never the hard part. The hard part is that working the list is repetitive phone-and-message work, and the sick animals in the building will always outrank it. So it waits, and every name on it drifts closer to being someone else's client.

Your competitor is not the corporate group up the road. It is the version of your own recall list that nobody has worked since Easter.

Start with the patients who never came back

Pick one workflow, not the whole clinic. For most independent practices the best place to start is the one that gets dropped first every busy week: lapsed recalls.

A system reads the due dates already sitting in your practice software, finds the patients overdue past a threshold you set, and messages each owner in your clinic's voice, not a vendor's template. It answers the easy replies, books the yeses into real gaps in the diary, chases the quiet ones twice, and puts the rest on a short list for a nurse to ring on a slow afternoon. Nothing about that requires a diagnosis. All of it requires persistence no human team has spare.

A recall you chased costs you a text message. A patient you lost costs you every visit they would have made for the rest of that animal's life.

That gives you a number to defend at the end of the quarter: lapsed patients contacted, bookings made, against what you spent. Arithmetic, not a vibe, and I set out how to run that calculation honestly in the AI ROI framework.

The second workflow, once the first is proven, is the front desk overflow: the calls that ring out and the no-shows that leave dead time in the diary. A system that answers the missed call, books the routine visit and escalates anything urgent to a human is doing reception work, at hours your receptionists cannot.

Automate the chasing, not the diagnosing

Here is the line that keeps this safe, and it is sharper in veterinary work than almost anywhere.

Diagnosis, treatment and prescribing sit with a registered vet. Your registration carries the responsibility, and no software vendor shares it. An imaging tool that suggests a finding is offering an opinion for a professional to weigh. The moment a system starts telling owners what their animal probably has, you have a professional conduct problem wearing a chatbot.

There is a cleaner place to point the same technology. Drafting the reminder, reading the reply, moving the booking, writing the note onto the file: that is admin. It was always admin. It is the part your team hates and the part a machine does without sighing.

Point the software at the work nobody wanted to do, not at the judgement you are registered to make.

What AI for vets costs

Work down this list in order and stop the moment something works.

• The tools already inside your practice software. Reminder runs, online bookings, waitlists. Often half-configured. Turn them on before you spend a dollar, because a build that duplicates them is money set on fire.
• A scribe or phone-answering subscription, priced per vet or per line each month. Cheap enough to trial in one consult room and judge on your own numbers.
• A custom build that connects recalls, replies and bookings to your actual practice software. Usually a few thousand up to the mid teens of thousands of dollars to go live, and what moves you up that range is how many systems it writes back into.

What catches owners out is the running cost, not the build: the subscriptions underneath, the model usage, and the nurse time spent on whatever the system escalates. I broke those layers down in what AI actually costs a small business. A vendor whose every answer is their priciest option is solving for their invoice.

The Australian layer: your practice software and client data

Two things separate a system that works in an Australian clinic from an overseas template.

The first is integration. You run on ezyVet, VetlinkPRO, RxWorks or Covetrus, and that database is the business. A tool that cannot read your real due dates and write bookings back has not removed the double handling, it has moved it to your nurses. Ask what it writes back, and where, before the demo wins you over.

The second is data. Client files hold names, addresses and payment details, and that is personal information under the Privacy Act even when the patient is a cat. Send it offshore and the cross-border rules keep you accountable for what the overseas recipient does with it. Ask where it is stored, whether it trains someone else's model, and whether you can delete a record on request. A vendor who cannot answer has told you how carefully they build.

Common questions about AI for vets

What should a veterinary clinic automate first?

Lapsed recalls, then missed calls. Not diagnostics. Prove one workflow before you widen, because switching on five things at once means you cannot tell which one paid.

Will AI replace vets?

No. The shortage is real and the judgement is licensed. The software clears the chasing and the paperwork so the vets you can hire spend their hours on animals.

Is a custom build worth it over what my practice software gives me?

Only after you have switched on what you already pay for and hit its limits, and only if you own the system and the data at the end.

Go back to Banjo. The clinic that has him now did not out-medicine you. It sent the message in the window when his owner was ready to book.

If you want a straight read on how much of next year's revenue is already sitting in your own recall list, that is what a first call is for. Book a strategy call and bring your overdue list and last month's missed-call count. We will find the patients you are quietly losing before we talk about building anything.