Updated 2026-09-24 · 4 min read
It's one of the most reasonable questions we get, and it usually comes from a salon that already has things in order: *«I've been with my software four years, I know it inside out, my data's in there. Can't I just put the AI on top of it?»*.
The honest answer is: sometimes yes, it's rarely that simple, and there's a third way that almost everybody ends up taking. Let's take it in order.
Why «putting AI on top» sounds easier than it is
For an assistant to close an appointment — not take a message, close it — it needs to do four things against your current software:
- Read your services, their durations and your stylists.
- Check what's genuinely free, right now.
- Write the appointment.
- Find out if you move or cancel it from inside the software.
All four require your software to have an API open to third parties. And there's the problem: most salon management systems don't have one, or they keep it for commercial partnerships. It isn't bad faith, it's their model: they live on their customers staying inside.
When there's no API, what you'll be offered is an assistant that converses beautifully and finishes with *«I'll pass this to the salon»*. That isn't automating: it's moving the work somewhere else. The front desk still has to type the appointment in.
The three real options
| A custom connector | An assistant that takes a message | An integrated system (ClaudIA) | |
|---|---|---|---|
| Requirement | Your software must have an API | None | None |
| Does it close the appointment itself? | ✅ If the API allows it | ❌ Somebody transfers it by hand | ✅ |
| Up-front cost | Development (thousands) | Low | None |
| Ongoing cost | Maintaining it every time the API changes | Subscription + your time | Fixed subscription |
| Who fixes it if it breaks | Whoever built it (if they're still around) | — | We do |
| Change software? | No, you keep yours | No | Yes, you change |
The first option makes sense when your software has an API and your volume justifies the development and its upkeep, which is the part almost nobody budgets for.
The second is the one most sold and the one that disappoints most at six months.
The third way: coexist, don't migrate in one go
What almost everybody does is neither of those. It's this: ClaudIA syncs with Google Calendar both ways. What it books appears in your calendar within seconds; what you block there (lunch, training, a day off) is respected and never offered to anybody. If your team already lives in the calendar on their phones — and most do — nothing about their day changes.
That allows a real period of coexistence:
- Weeks 1-2: ClaudIA only handles WhatsApp and Instagram. Your software stays your software. You watch whether the appointments coming in are good ones.
- Weeks 3-4: you switch on the phone, and only for the calls you can't take. Your line still rings first.
- After that: you decide, with a month of real bookings in front of you. No lock-in.
For your client base there's CSV import from the dashboard: it only adds new records, never overwrites an existing one. From then on, every appointment that comes in fills in each record's history.
What you gain by having it all in one place
- One calendar for every channel. WhatsApp, Instagram and the phone book against the same slots, so two people never get the same time. And it adapts to how you work: that's what the article on variable timings is about.
- One party responsible. If something goes wrong, nobody has to work out whether it was the connector, the software or the assistant: we fix it.
- Your data, always yours. Clients, appointments and history are exported from the dashboard whenever you like, with no lock-in.
- Your own channels, no commission. ClaudIA converts the people already writing to you, without charging per new client.
How to decide it in five minutes
Ask your current supplier, in writing, two things:
- Do you have a public API for checking availability and creating appointments from another tool?
- Is it documented, and can I give it to whoever I choose?
If the answer is yes to both, you have an option many don't: keep your software and build the AI layer on top. If it's no — and it usually is — then the real choice isn't *«integrate or change»*, it's *«carry on answering it myself, or change»*.
In the demo you connect it to your Google Calendar and watch appointments come in on their own, without touching the software you already use. With that in front of you, deciding is much easier.