Aesthetics center AI training: a step-by-step guide

An aesthetics or beauty center’s inbox always fills up with the same questions: "How much do fillers cost?", "When do you have an opening for laser?", "Should I get botox or fillers?", "When can I return to work after the procedure?". Medical aesthetics, laser hair removal, skin care, permanent makeup: whatever the service, the same twenty questions come in a hundred times a day. While reception tries to keep up with the phone and WhatsApp, dozens of "price?" comments pile up under a before/after post, and a message that comes in after hours in the evening waits until morning. Every consultation request answered late goes to another center.

inTusell takes over this load. But to do that, it first needs to learn your center, your services, and your operating routine. This article explains how an aesthetics / beauty center trains the inTusell AI from scratch, step by step. This is the aesthetics chapter of our sector-based "how to train your AI" series, and it is the series’ main article.

Quick answer

Why does training matter?

inTusell is not an off-the-shelf chatbot; it is an AI assistant that behaves like an experienced receptionist and client coordinator. No good coordinator starts on day one without knowing the center: they need to know which services you offer, your consultation routine, and which questions to leave to the specialist. Training teaches the AI to do two things well. First, give the right information: your services, preparation instructions, working hours. Second, stop at the right boundary: leave the procedure decision to the specialist, and never promise outcomes.

An untrained assistant either gives overly generic answers or guesses on a topic it doesn’t know. In aesthetics, guessing is dangerous. Wrong preparation information wastes an appointment, and a boundary-crossing line like "it will definitely look great on you" both misleads the client and violates health advertising regulations. A well-trained assistant stops when it doesn’t know and directs the client to the specialist.

Who is it for?

This guide is for aesthetics / beauty businesses whose inbox is dominated by consultation requests and who answer the same questions over and over again:

• Medical aesthetics centers and dermatology clinics (botox, fillers, laser)
• Laser hair removal and skin care centers
• Beauty salons and businesses offering permanent makeup and skin analysis
• Teams with heavy traffic of free pre-procedure consultations
• Centers receiving dozens of appointment requests a day from Instagram and WhatsApp

You don’t need a technical team. All of the steps below are completed from sections in the panel, without writing code.

The structure of training: 5 core steps + 2 continuous steps

Splitting the training into two groups makes your job easier. The first 5 core steps get the assistant up and running; these steps are the one-time part of the setup. The 2 continuous steps that follow (reviewing and turning fixes into rules, and opening channels) are the ongoing part that you sharpen as you use the assistant. You’ll find all of them in order below.

1. Upload the knowledge base

The foundation of training is the knowledge base (RAG). Under My business › Knowledge › Knowledge Base, you upload your center’s information. Each time the AI generates a response, it automatically searches these sources and uses only the information written there.

Supported source types:

Every file you upload is automatically chunked and made searchable with pgvector. When you upload a "pre-laser preparation" document, the AI finds the right paragraph and responds when a client asks "Can I sunbathe before the procedure?".

What an aesthetics center must definitely upload: service and procedure descriptions, pre/post-procedure care instructions, working hours, team information, payment/communication policy, and the most frequently asked questions. An important limit: the knowledge base is not for medical advice text. The AI uses the information here to answer "what do you offer, how do you prepare" questions; it leaves medical questions like "I have this, which procedure would be good for me?" to the specialist.

2. Set up the consultation appointment system and working hours

The knowledge base covers "what you offer"; the appointment system lets the assistant give the client an actual time. In aesthetics, the heart of this step is the free consultation appointment, because most procedures already start with a specialist evaluation. In the panel you define three things:

Once these three are defined, the AI no longer invents times; it suggests appointments based on your working hours and full slots. The system blocks two appointments at the same time (double-booking). If Google Calendar is connected, each new appointment is also copied one-way to the team’s calendar; an event you add in Google by hand does not block that time in inTusell. A reminder goes to the client 1 day and 2 hours before the appointment (on paid plans); the 1-day message asks "1 Yes · 2 Reschedule · 3 Cancel" and carries a change/cancel link.

We’ve gathered all the details of the consultation appointment engine (durations, break times, conflict prevention, reminders, and calendar sync) in a separate article: aesthetics consultation and appointment automation. You can also see the service and appointment capabilities on the solutions page and the aesthetics / beauty center solution page.

3. Set the persona and tone

You taught the AI what to say in the first two steps; now you’ll define how it will say it. There are two settings in the panel:

• Assistant name: The name it will introduce itself with to the client. Most aesthetics centers choose a warm, reassuring name.
• Tone: For health, the default tone is professional; warm but measured, calm and reassuring. Emoji use is limited and sales pressure is kept low.

Health mode is deliberately more cautious than other sectors. Even the greeting message points the client in the right direction. A typical opening reads like this: "Hello. How can I help you? For suitability for your procedure, please consult our specialist during a consultation." That single line carries both the center’s tone and what the regulations require.

A multilingual note: the AI replies in whatever language the client writes in. For messages arriving from abroad in English, Arabic, or German, you do nothing extra. The assistant detects the language on its own and answers in it while keeping the health tone. Fixed system messages such as reminders go in Turkish to Turkish speakers and in English to everyone else.

4. Define the response rules and health limits

The persona defines "who it is," and the response rules define "how it will behave." In aesthetics, this step does two jobs at once: conveying your sales discipline and drawing the health limits. With the AI Manager Chat, you add rules by writing in plain language, just as you would instruct a teammate; you see the rules in AI Rules and switch ready rule packs on or off in the Behavior Library.

Typical rules for aesthetics centers:

• "Before the appointment, ask about the client’s request and expectations, but do not recommend a procedure or give advice."
• "When asked about the procedure fee, do not quote a price; say the fee will be finalized after the consultation and direct them to an appointment." (Can be changed according to your center policy.)
• "Do not guarantee outcomes; do not use phrases like 'definitely goes away/guaranteed/it will look great on you.'"
• "In situations such as a medical complaint, allergy, or pregnancy, direct the client to the specialist."

The most common mistake in aesthetics is misleading the client, and running afoul of regulations, with a single boundary-crossing sentence. In inTusell, this boundary is not left to the rules you write alone; two layers work together. The real control is health mode’s system instruction: the AI is constrained from the outset to use only the information in the knowledge base, recommend no procedure, and hand off when unsure. The second layer is an output filter: it scans for misleading health claims such as "guaranteed result," "certain cure," "no side effects," or "Ministry of Health approved" with a pattern scan and a second-model check, and flags them. It runs in shadow mode by default, so it does not block the response; it detects and flags it. The filter is an extra safety net, not a guarantee; the real control is the system instruction and your rules.

To compare two AI tones, you can use the A/B test, which is in beta: for example, a more formal and a friendlier tone run side by side, each on half of the replies, and the experiment card shows which one leads to more wins. Today only the tone changes; the content and the rules stay the same.

5. Teach from past conversations

This is the step that moves training from "good" to "specific to your center." In the panel, you upload audio recordings of your past client conversations (MP3, MP4, WAV, M4A) and mark each one as Won or Lost, for example, whether the client came to the consultation and accepted the procedure, or was lost.

The system uses these recordings in two ways:

This way, the AI learns how your best coordinator put the client at ease and moved someone who said "let me think about it" toward a consultation. Uploading requires explicit consent; phone numbers, emails, ID and card numbers are masked in the transcript before processing. Because aesthetics data is special-category, this protection matters even more here.

This step is not mandatory, but don’t skip it. The knowledge base teaches the AI "what" it knows; past conversations teach "how you coordinate." When the two are combined, the assistant truly resembles an experienced client coordinator.

6. Review and turn fixes into rules (ongoing step)

The first five steps get the AI up and running. What follows is the continuous part that sharpens it over time. You check replies in two places: in AI Test, by asking questions the way a client would, and in Conversations, by reading real chats.

Say the AI explained a care instruction incompletely, or referred to a procedure by the wrong name. You add the missing fact to the knowledge base or write a rule in AI Rules (for example, "always refer to procedures by the name on our service list"); the next reply works from that source. Over time, rules specific to your center build up (the procedure names you use, your standard informational sentences, your consultation-directing style). If you want to see each reply before it goes out, put the account in Full approval mode, or a single conversation in Approval mode.

The Label Manager is a quality record: satisfaction replies, the outcome of a handed-off conversation, won/lost classifications and labels added by hand land there for your approval. Approvals and corrections are kept as a record; today they do not change how the AI writes replies on their own. In the first weeks, we recommend a short look every day.

7. Open the channels (continuous step)

Once training is ready, you put the assistant in front of clients. inTusell gathers all channels in a single inbox: Instagram DM, Instagram comments, WhatsApp, Telegram, and Web Chat.

Channel-opening methods:

• Instagram: connected through Meta login; you pick your Facebook Page and Instagram account. The account must be a professional account linked to a Facebook Page.
• WhatsApp: under My business › Channels › Messaging Channels you click "Connect with QR" and scan the code with your phone; your number stays the same and no Meta Business approval is required. The official WhatsApp line (Cloud API) opens after Meta approval; today you connect with a QR code or with an 8-character linking code for your phone number.

DM replies are already on once Instagram is connected. Comment replies have their own switch on the Instagram card ("Instagram comments"), on by default. If you like, you can switch it off, answer the comments under before/after posts by hand for a while, and switch it on when you’re ready. To stop the AI answering a channel, turn that channel off ("Instagram DM", "Instagram Comments") in the channel list in the AI settings. If you connected Instagram before September 24, 2026, you need to reconnect it once for comments.

The account mode decides how independently the AI works (My business › Instructions › AI Settings › Advanced AI Settings):

In every mode the AI handles appointment and information traffic; conversations requiring a medical evaluation are handed to the specialist and land on the Decisions screen with the full history. If you want one conversation to behave differently, switch just that conversation to Approval, Shadow or Paused. For the details of Instagram and WhatsApp automation: Instagram and WhatsApp automation for aesthetics centers.

How long does training take?

How long it takes depends mostly on whether your documents are ready. The steps of a working setup:

1. Uploading the first files to the knowledge base (the quickest step if your documents are ready)
2. Consultation appointment types and working hours
3. Persona, tone, and first response rules
4. Connecting channels

But there is no moment when "training is done." In the first weeks, as you add what you notice in AI Test and in real conversations to the knowledge base and the AI rules, the assistant gets sharper for your center; uploading past recordings and trying tones with the A/B test keep improving it after that. Setup is done once; mastery is continuous.

What it isn’t

inTusell is an AI sales assistant and CRM that answers messages on WhatsApp, Instagram and web chat, books appointments and opens orders, and follows each customer through the sales pipeline; it is not a simple chatbot. Putting it in the right category matters, because the wrong expectation leads to the wrong setup.

• It is not a specialist or an evaluation tool. It does not recommend a procedure, give advice, or say "this would suit you." It directs the medical decision to the specialist and the consultation.
• It is not a tool that diagnoses from a photo. Even if the client sends a "before" photo, the AI does not evaluate it and recommend a procedure; it leaves the assessment to the specialist and directs the client to a consultation.
• It is not a marketing tool that promises outcomes. Phrases like "certain result/guaranteed" break the regulations; the sector instructions tell the AI not to use them, and the output filter flags such phrases.
• It is not an intermediary that replaces the center. The center always provides the service and issues the invoice; inTusell is not a party to payment.

In short: not a bot that gives canned answers, but a client assistant that represents your center to the extent you train it and is set up to stay within the medical boundary.

Frequently asked questions

How long does aesthetics center AI training take?

A working setup comes down to these steps: uploading the knowledge base, consultation appointment types and working hours, persona and tone settings, and a few response rules. How long it takes depends mostly on how ready your documents are; the real refinement comes in the first weeks, as you add what you notice in AI Test and in real conversations to the knowledge base and the AI rules. Training is not a one-time job; it is continuous.

Does the AI recommend a procedure or give medical advice to the client?

No. In health mode the AI does not diagnose, recommend a procedure/treatment, or guarantee outcomes; it directs questions like "what would suit me" or "which procedure should I get" to the consultation and the specialist. The primary safeguard is the "do not give advice" instruction that health mode gives the AI; in addition, an output filter (a pattern scan plus a second-model check) scans for and flags misleading phrases such as "guaranteed result" or "definitely goes away."

Do I need technical knowledge to train the AI?

No. All training is done from the panel; no code, API key, or developer is required. You upload PDF/Excel files to the knowledge base, enter consultation appointment types and working hours, and write response rules in plain language. You connect Instagram through Meta login and WhatsApp with a QR code.

Are client data and photos safe under KVKK?

Health data for aesthetic procedures and "before" photos are special-category personal data under KVKK and require explicit consent. In inTusell, data is stored encrypted and each business’s data is kept separate; the AI does not save the high-sensitivity health-note field without your confirmation. Consent is recorded per channel and purpose, with its time; the client can change their choice through a consent portal link.

Does the AI quote a procedure price?

That depends on your center policy and health advertising regulations. It does not market procedure fees on public channels; in a typical setup it defers the fee until after the consultation or directs the client to the live team. When it is unsure, it does not invent a price.

Does the AI create the consultation appointment on its own?

Yes. The AI recommends the appropriate consultation type and creates the appointment while accounting for working hours and full slots; double-booking the same time is prevented by the system. In cases requiring a procedure decision or medical evaluation, it hands the conversation off to the specialist and the live team.

Next step

You’ve trained your assistant; next comes using it in daily operations. The next article in the series explains how to run the inTusell you trained on a real workday: incoming consultation requests, calendar, reminders, reducing no-shows, and handing off to the team. Continue straight from there: how an aesthetics center uses inTusell.

If you’d like to compare this series with your own sector, the other main guides: AI training for Instagram boutiques, tour agency AI training, and clinic AI training. You can find the entire aesthetics solution on the aesthetics / beauty center page.

If you’d like to see it live before starting the setup, use Get a demo and we’ll open your panel together in a short session, or write to hi@intusell.com. For package and quota details, you can check the pricing page, and for other guides, take a look at the all articles list.