How a clinic uses inTusell: a daily operations guide

In the main article, you trained the inTusell AI: you uploaded the knowledge base, set up appointment types and working hours, and configured the persona and health boundaries. Training was a one-time setup. Now the real work begins: how does a clinic use inTusell, that is, how does clinic inTusell usage work in daily operations? This article shows, step by step, what the assistant you trained actually does in the field over a working day, from the incoming DM to the appointment, from reminders to reducing no-shows and handing off to a human.

This article is the second part of the health section of our sector-based "how to train your AI" series. The first part, how to train the inTusell AI, covered the setup; this one covers turning that setup into daily operations.

Quick answer

A day in the flow

A day at a clinic that has set up inTusell looks very different from before. Reception used to arrive in the morning and work one by one through dozens of unread DMs and unanswered comments. Now, in Intern mode, the messages that came in overnight are already answered, appointments are created, and reminders are scheduled; in Full approval, where a new healthcare account starts, the replies and bookings prepared overnight wait for your approval in the morning. The backbone of a day works like this:

The team no longer spends the day sifting through messages. It deals with the conversations that genuinely need a decision, medical ones in particular.

Who is it for?

This usage model makes the most sense especially for these clinics:

• Clinics that receive heavy appointment demand via Instagram and WhatsApp: those who can’t keep up with dozens of "is there a slot?" messages a day.
• Clinics that suffer from no-shows (patients who don’t turn up): centers where empty slots become lost revenue.
• Clinics that lose after-hours demand: those losing patients because appointment questions that come in during the evening and on weekends are answered late.
• Centers that work with health tourism: those who have to respond to international patients in multiple languages for hair transplants, dental, and aesthetics.

If you have a volume of demand that a single reception desk can’t keep up with, inTusell works like an experienced prospect coordinator that handles that demand.

Incoming demand: the patient asks, the AI suggests the right service

The flow starts when the patient sends a message. Imagine someone writing on Instagram DM, "Price and available day for a dental cleaning?" The AI reads this message, scans the service descriptions in your knowledge base, suggests the service that fits the patient’s need, and steers toward an appointment.

There are two important boundaries. First, the AI does not diagnose. On "My tooth hurts, what could it be?" it doesn’t list possible causes; it leaves the situation to the physician and steers toward the appropriate appointment. Second, the AI replies in whatever language the patient writes in, which is critical for international patients.

If during training you added the rule "before the appointment, ask about the request and availability, but don’t diagnose," the AI first clarifies the service, the date range, and the patient’s availability. We cover separately how all these channels come together in a single inbox in the Instagram and WhatsApp appointment automation article.

Booking an appointment: slot, duration, and conflict prevention

When the patient asks for a time, the AI doesn’t pull a time out of thin air. It looks at the three things you defined during training: the duration of the appointment type (for example, "First Examination 30 min"), your working hours, and whether that slot is taken. If it finds a suitable slot, it creates the appointment.

Here the most critical safeguard is conflict prevention: two appointments cannot be entered for the same time. Before creating an appointment, inTusell checks your working hours and existing appointments; if a conflicting slot is requested, it doesn’t open the appointment. Cancelled or no-show (missed) appointments free the slot again in this check. So the nightmare that clinics working with a manual planner experience most often (booking two patients for the same time) disappears.

Every appointment has a status, and its lifecycle is clear:

scheduled
  → confirmed
  → attended
or
  → cancelled
  → missed (no-show)

You’ll find detailed instructions on how to set up appointment types, durations, buffer times, and calendar sync in the clinic appointment automation article.

Reminders and reducing no-shows

The most expensive thing in a clinic is a patient who doesn’t turn up: an empty slot is both lost revenue and a missed chance for another patient who could have taken that time. inTusell reduces this with automatic reminders.

For every appointment, two reminders are scheduled:

• 1 day in advance: a message along the lines of "You have an appointment tomorrow at [date time]"; it asks "1 Yes · 2 Reschedule · 3 Cancel" and the answer is recorded on the appointment.
• 2 hours in advance: a short reminder along the lines of "You have an appointment today at [time]".

The reminder goes through the channel the patient wrote on; if that channel is unreachable, SMS kicks in when an SMS provider is set up, and if that fails too, email. The message contains a change/cancel link; if the patient lets you know in advance that they can’t make it, the slot becomes free again. If you want to turn off the reminder for a specific appointment, you can do that per appointment too. Reminders run on paid plans; on the Free plan automations are off.

If the patient still does not show up, you mark the appointment with the "No-show" button in the Agenda or Day view; an appointment still not marked "Attended" about 2 hours after it ends also counts as missed, and the conversation moves to the "needs follow-up" stage. If you mark attendance in the panel (at least one "Attended" in the last 30 days), inTusell sends the patient who did not show a rescheduling message with 3 numbered options from your real open times and an appointment management link; if you do not mark attendance, it does not send it, because "missed" is then only a guess and telling someone who did come "we missed you" is worse than not writing at all. The patient can move the missed appointment to a new time from their own link within 7 days.

Price and regulation

Treatment fees are a more sensitive topic for a clinic than the pricing matrix in tourism. Health regulations restrict both the public marketing of treatment fees and the promising of outcomes. The AI holds this line:

• It doesn’t discuss treatment fees in public comments; it invites the patient to send a DM.
• In a typical setup it steers toward an appointment by saying the fee "becomes clear after the examination/consultation" (this can be changed per your policy).
• Phrases like "guaranteed result" or "definite success" are forbidden; the sector instructions tell the AI not to use them, and an output filter (a pattern scan plus a second-model check) also flags such promises.

So rather than inventing a figure it isn’t sure of, the AI steers toward the right step: the examination or the live team. For product and pricing details, you can check the solutions and pricing pages.

KVKK and special-category data

Health data is special-category personal data under KVKK (Turkey’s data protection law), and processing it is subject to strict conditions. These are the tools in inTusell that support this side:

1. Consent record: The patient’s consent is recorded per channel and purpose, with its time; you can also send the patient a link to manage their consent.
2. Sensitive-field control: The AI never saves a high-sensitivity field such as a "health note/complaint" on its own; it asks for confirmation every time.
3. Legal notices: "Legal notices" under My business › Business Info sends your patients a KVKK notice with your own privacy link (a first-contact note, an opt-out line in promotional messages). It is on by default; only the owner or an admin can change it.
4. Storage and masking: Data is stored encrypted and each business’s data is kept separate; if you set a retention policy, expired records are deleted nightly. In the sales call recordings you upload, phone numbers, emails, ID and card numbers are masked in the transcript. "Download My Data (KVKK)" gives you an export of your data.

This makes it easier, in the event of an audit or objection, to answer the question "what did the patient consent to, and when?" from the record.

Following up a quiet prospect: proactive follow-up and CRM

In a clinic, most appointments are lost to prospects who say "let me think about it" and then disappear. inTusell doesn’t forget these prospects. To someone who got the information and then went quiet, the AI writes up to 3 follow-up messages; they are not templates but written for the conversation, and they go out only within business hours (your appointment hours, otherwise 09:00-21:00 local time) on WhatsApp, Instagram or Telegram. Follow-up stops when the prospect replies, books an appointment or says "don’t write to me". Every conversation is logged to the CRM, so the prospect’s history, the service they were interested in, and the stage they’re at all stay on record.

So when the team sits down to work in the morning, it’s already clear which prospect is hot and which is waiting on follow-up. Nobody has to keep a manual reminder list.

The clinic pipeline

Every prospect moves along a health-specific pipeline, and the AI advances them to the right stage as the conversation develops. The stages of the health template are:

Yeni Hasta / Talep      (New Patient / Inquiry)
  → Randevu Alındı        (Appointment Booked)
  → Muayene / Konsültasyon (Examination / Consultation)
  → Tedavi Planı Sunuldu   (Treatment Plan Presented)
  → Ödeme / Onay           (Payment / Approval)
  → Tedavi Başladı         (Treatment Started)
  → Tedavi Tamamlandı      (Treatment Completed, marked as won)
or → Vazgeçildi            (Dropped, marked as lost)

The pipeline shows you at a glance which prospect only got information, which booked an appointment, and which is waiting on a treatment plan. When the AI creates an appointment, it automatically moves the prospect to the "Appointment Booked" stage.

Handing off to a human: working modes

You decide how independently the AI works. You pick the mode under My business › Instructions › AI Settings › "Advanced AI Settings":

In every mode, the AI hands a question requiring a medical decision or a sensitive situation off to the team; the handoff lands on the Decisions screen with the full history, so the patient doesn’t have to start over. You can also switch a single conversation to Approval, Shadow or Paused; that affects only that conversation.

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. To put it in the right category, let’s also clarify what it isn’t:

• It isn’t a physician or a diagnostic tool. It doesn’t diagnose, doesn’t recommend treatment/medication; it leaves the medical question to the physician.
• It isn’t an HIS / EMR (patient record system). It doesn’t keep medical records; it’s the appointment, communication, and prospect-coordination layer.
• It isn’t a collections agent. The clinic provides the service and issues the invoice; inTusell is not a seller or intermediary.
• It isn’t priced specifically for health. Plans differ only by messages, voice minutes and storage, and don’t change by sector. The appointment module can be enabled on any plan; automations such as reminders and follow-up are on paid plans.

Let these boundaries be clear from the start, so you don’t begin with the wrong expectations.

Frequently asked questions

Does the AI create the appointment on its own?

Yes. The AI suggests the appropriate service and creates the appointment based on working hours and open slots. Double-booking the same time is prevented by the system. When a medical decision or complex situation is required, it hands the conversation off to the live team.

How are no-shows (patients who don’t turn up) reduced?

For every appointment, an automatic reminder goes out 1 day and 2 hours in advance; the 1-day message asks "1 Yes · 2 Reschedule · 3 Cancel" and carries a change/cancel link. An appointment still not marked "Attended" about 2 hours after it ends counts as missed, pending reminders are cancelled and the conversation moves to the "needs follow-up" stage. If you mark attendance in the panel (at least one appointment marked "Attended" in the last 30 days), the patient who did not show gets a rescheduling message with 3 options from your real open times and an appointment management link; if you do not mark attendance, this message is not sent, because "missed" would only be a guess.

Which channel does the reminder go through?

First through the channel the patient wrote on (WhatsApp, Instagram, Telegram); if that’s unreachable, by SMS when an SMS provider is set up, and if that fails, by email. The patient doesn’t need to install a new app. Reminders run on paid plans; on the Free plan automations are off.

Does the AI quote the treatment price?

It depends on your clinic policy. Health regulations restrict publicly marketing treatment fees; in a typical setup the AI defers the fee to after the examination/consultation or routes it to the live team, and never invents a figure.

Can the patient be connected to a human?

Yes. When the AI is unsure or a conversation needs a person, it hands off to your team; the handoff lands on the Decisions page with the full conversation history. You can take over any conversation at any time, or switch just that conversation to Approval, Shadow or Paused.

Do appointments land in Google Calendar?

Yes. When an appointment is created, it’s copied to Google Calendar as "Appointment: patient name"; reschedules and cancellations are reflected too. The sync is one-way (inTusell → Calendar): the team sees the appointments in their own calendar, but an event you add in Google by hand does not block that time in inTusell.

Next step

If you haven’t trained your assistant yet, start first with the how to train the inTusell AI article: the foundation of this operation is set up there. If you want to go deeper on the channel side, you can move on to the Instagram and WhatsApp appointment automation article, and for the details of the appointment engine, the clinic appointment automation and no-show reduction article. The ready-made clinic setup is on the clinic solution page, and you can see the whole series on the all articles page.

To see live how it would work in your own clinic, request a demo or write directly to hi@intusell.com. In a short session, we’ll open your inbox together and test the first appointment in the system.