All cases
Studio case // EST.EPIL // YCLIENTS

EST.EPIL: an AI receptionist connected to YCLIENTS

A client asks for a massage appointment, and the assistant interprets part of the word as a month. The reply sounds confident, but the booking fails. For EST.EPIL we connected the assistant to YCLIENTS and worked through the complete booking process, from a natural-language request to a confirmed CRM operation.

Channels
Website widget and Telegram
Operational data
Services, prices, staff and slots from YCLIENTS
Operation result
A CRM-confirmed booking or a task for a receptionist

What we built

A shared assistant workflow for the website and Telegram. It finds a service, reads current prices and available slots from YCLIENTS, collects booking details and creates the appointment after confirmation. Rescheduling and disputed requests go to a receptionist with the conversation context.

Why website content was not enough

The first assistant answered from website material. Price columns were mixed up during extraction, and the model tried to fill missing details itself. Booking data changes throughout the day, and services vary between locations.

We kept studio policies in the knowledge base and connected tools for prices, services, staff and availability. The model interprets the request; server code validates parameters and the CRM response.

The Alice widget on the public EST.EPIL website

Website widget captured on 25 September 2026. The image shows its greeting, not a customer conversation.

Open full-size image ↗

The booking workflow

  1. 01Map the client's wording to a service and location in YCLIENTS.
  2. 02Read available dates and times, clarify the staff member and collect required details.
  3. 03Show the proposed appointment and wait for the client's explicit confirmation.
  4. 04Check the slot again before creating the booking. Confirm success using the record ID returned by YCLIENTS.
  5. 05Hand off rescheduling, occupied slots and ambiguous API responses to a receptionist.
Workflow diagramGERON LABS

When a booking is actually confirmed

  1. Service, location and date

    Clarify the missing details of the request.

  2. Available slots from YCLIENTS

    Read availability and get the customer's selection.

  3. Create the booking

    Use the required permissions; do not blindly retry a write after a timeout.

  4. Verify the API result

    Store the booking ID. Hand errors or missing access to reception.

EST.EPIL booking workflow. A widget greeting or CRM event alone is not proof of a completed booking.

Failures we worked through

A date parser treated the beginning of the Russian word for massage as a month abbreviation. Tools now receive a normalized date with a separate calendar check. Code calculates the weekday.

Repeated discounts and contact requests were limited by context. Empty model replies, service-name mismatches and unavailable slots became additional cases to check against real conversations.

What the receptionist receives

A handoff includes the contact, reason and relevant conversation context. Tool events and history show the step where the booking stopped. Returning clients retain the operational context of previous conversations.

Requests requiring a specialist remain with a person. The number of CRM calls alone does not measure completed customer visits.

The operational result

Consultation, availability checks and booking creation follow one route. Exceptions reach a receptionist with the details already collected, and the route can be checked through CRM failures and unfinished appointments.

The project established concrete requirements for an AI receptionist: current prices, slot revalidation, confirmation before an action and a usable human handoff.

Sources and links

SYS: COOKIE

We use technical browser storage so the site works correctly. Privacy Policy