Skip to content
VC
Methodological proof of concept. Haven't done this specific case as an external client project yet — it's the architecture and stack I'm ready to deliver. Numbers in the cards are targets based on typical RU SMB benchmarks. For first clients in this niche: −30% off list + 90 days extended warranty + case-study rights.
Ready to deliver · 24/7 client booking

Voice agent Vapi + YClients: 24/7 booking without an administrator

A chain of three premium salons in Moscow was losing up to 40% of calls in the evenings and on weekends. A night-shift administrator at ₽95k/mo didn't solve the problem. A voice agent on Vapi + GigaChat with direct YClients booking delivered 97% pickup and brought +₽278k revenue per location.

Industry
Beauty salon chain (3 locations)
Stack
Vapi · GigaChat · YClients API
Timeline
~5 weeks
Outcome
Pickup 64% → 97%
01 · Pain Point

A 21:30 call goes nowhere

Premium beauty segment works on a simple rule: the client calls and books when they think of it — during lunch, on the way home, in bed before sleep. If no one answers at that moment — they WhatsApp a competitor and never come back.

The three salons' administrators handled incoming calls 10:00-21:00. After 21:00 and on weekends calls went to voicemail no one checked in the morning — by the time they called back, the client had already booked elsewhere.

An attempt to hire a night-shift staff for evenings and weekends at ₽95,000/mo per location didn't solve it: the duty staff didn't know the masters' specifics, got confused with rooms, missed calls during bathroom breaks or lunch. Pickup rate still hovered around 64% across working and non-working hours.

02 · Solution

Voice agent on Vapi + GigaChat → direct booking to YClients

Vapi answers calls 24/7. GigaChat 2 Max is the dialogue brain, knows services, masters, rooms, prices, and the schedule of three locations. FastAPI middleware converts agent intents into YClients REST API calls: check open slots, book, reschedule, cancel, send SMS confirmation via SMSC.ru.

01
Vapi inbound

Replacement number behind the main, Yandex SpeechKit for STT/TTS in Russian

02
GigaChat 2 Max

14 scenarios: new booking, reschedule, cancel, pricing, master consultation

03
FastAPI middleware

Agent tool calls → YClients REST: slots, bookings, client, history

04
YClients API

Direct booking to the right room at the right location, conflict checks

05
SMS + fallback

SMSC.ru confirmation to client; confidence < 0.7 → switch to admin

14 scenarios instead of one script

A beauty voice bot isn't "book a haircut". It's a builder: "I want Katya for manicure, but no earlier than Thursday evening", "can I move Tuesday's appointment to Friday", "how much is coloring with a top master", "any open slots for facial massage this week". GigaChat 2 Max confidently handles each of these scenarios because prompt engineering was tailored to the specific YClients account: services, masters, durations, rooms, prices — everything is loaded from the API into the model's system context at session start.

Fallback to administrator on low confidence

If the agent fails to understand the request after 2 clarifications — the dialogue immediately switches to a live administrator (daytime) or goes into the callback queue (night). This is not "a bad booking is better than none": in premium segment a bad experience costs more than a lost booking. The confidence threshold was tuned iteratively over the first two weeks of launch.

YClients tool calls as first-class operations

FastAPI middleware doesn't "make the request for the agent" — it exposes the agent a set of tools: find_slots, create_record, reschedule, get_master_info. The agent decides which to call in what order. Middleware validates parameters and proxies to YClients REST with proper authorization.

SMS confirmation via SMSC.ru

After a successful booking the client gets an SMS with a link to the YClients booking card — they can view/reschedule/cancel via the standard salon interface, as if an administrator had booked it.

03 · Stack

Russian providers + predictable hosting

Vapi

Voice platform: number provisioning, ASR/TTS pipeline, WebSocket to LLM

GigaChat 2 Max

LLM dialogue brain, tool-calling, supports 14-scenario context

Yandex SpeechKit

STT/TTS in Russian — premium voices, not 'robot assistant'

YClients REST API

Booking/reschedule/cancel directly into salon rooms

FastAPI middleware

Tool server: validation, authorization, routing across 3 locations

SMSC.ru

SMS confirmation to client with link to YClients booking card

Selectel VPS

Middleware hosting in RF — FZ-152 compliant

PostgreSQL

Dialogue logs and quality metrics for iterative prompt tuning

VapiGigaChat 2 MaxYandex SpeechKitYClients RESTFastAPISMSC.ruSelectelPostgreSQL
04 · Results

What changed in numbers

Pickup rate
64% 97%

across all incoming, including 21:00-10:00 and weekends

Revenue per location
+₽278k

per month — bookings outside business hours, 41 on average

Night-shift cost
₽95k ₽8k

recurring per month: Vapi minutes + GigaChat tokens + Selectel

The headline number for the owner — +41 bookings per month per location from "off-hours" time. These aren't clients taken from the day administrators, it's a brand-new stream — those who used to drop after 5 rings.

Recurring cost dropped 12×. The day administrator continues to work in the salon — they're no longer a "phone dispatcher" but a reception consultant who greets clients in person.

05 · Where it fits

Where else the same architecture fits

Universal pattern — "Voice + LLM + CRM API + human fallback". The same architecture (just swap the CRM integration nodes) fits for:

  • Barbershops, nail studios, massage rooms on YClients/Altegio/Beauty Pro
  • Fitness clubs and training studios — class booking, cancel, membership rollover
  • Auto services with booking into Alpha-Auto or own CRM
  • Language schools, tutors, early-childhood centers — trial-lesson booking
  • Delivery / cleaning services — handling orders and reschedules outside business hours
What's reused on subsequent projects
  • FastAPI middleware scaffold with tool-call API and dialogue logging
  • Prompt engineering for GigaChat with service-catalog loading from CRM into system context
  • Confidence-fallback to administrator by two criteria: ASR quality and intent confidence
  • Selectel middleware hosting with proper PII storage schema for FZ-152
Similar challenge in your business?

If you have a CRM with a schedule and missed calls — a voice agent will close them

Vapi + GigaChat + your CRM — 4-6 weeks from kickoff to production. Payback typically fits in 2-3 months from freed administrator hours and intercepted bookings outside business hours.

Готовы начать?

Аудит за 5 000 ₽ — с конкретным отчётом и сметой

Расскажу что внедрить в вашем бизнесе в первую очередь, какая будет окупаемость, и нужен ли вообще AI для вашей задачи (иногда — нет).

Или просто напишите свой вопрос — отвечу в течение 2 часов