NuFace Maxillofacial & Dental Hospital
Client Snapshot
NuFace Maxillofacial & Dental HospitalHealthcare — Dental / Maxillofacial, SuratSize: 50
NuFace Maxillofacial & Dental Hospital is a multi-specialty maxillofacial and dental hospital based in Surat, Gujarat, covering Maxillofacial Surgery, General Dentistry, Orthodontics, Implants, Endodontics, Periodontics, Pediatric Dentistry, Cosmetic Dentistry and Prosthodontics. Patient enquiry volume runs through the hospital's phone line — a high-frequency inbound channel for appointment booking, rescheduling, cancellation, and pre-visit FAQ across patients calling primarily in Gujarati and Surat-style code-mixed Hindi-English.
Caller Digital’s Conversational AI
Caller Digital deployed Anaya — an inbound voice AI receptionist built on the Caller Digital platform and integrated with NuFace's on-premise HMS/CRM. Anaya is configured as a 15-stage finite state machine over a real-time Gemini Live model, with a two-layer prompting architecture: a BASE layer set at session start containing persona, voice, language and guardrails, plus a STAGE layer pushed per state transition with the current stage, the conversation state so far, and the next tool to call. This design stops the bot from re-asking captured information, narrating its own guardrails aloud, or looping on stale instructions. The agent handles appointment booking (new and existing patients, classified via /crm/patient on phone number), rescheduling, cancellation (with explicit yes/haan confirmation), appointment lookup, real-time doctor availability fetch from the HMS, full booking write-back to the HMS, Ahmedabad/Surat-style trilingual code-mixing (Gujarati default, Hindi, English), and an emergency-keyword router that routes safety triggers to the emergency line without further questioning.
Anaya is live as the hospital's inbound voice receptionist, integrated with the live on-premise HMS/CRM. Real-time doctor calendar reads, appointment write-backs, reschedule and cancel operations all flow through the live HMS API verified on 14 May 2026. The 15-stage architecture handles new-patient onboarding (name and age capture), OLD-patient recognition (auto-fill from /crm/patient response), and the full booking / reschedule / cancel / lookup workflow inside a single inbound conversation. The agent's BASE-vs-STAGE prompt split eliminates the most common voice-AI failure modes — re-asking captured fields, guardrail leakage into spoken audio, looping — which are the failure modes that previously made automated reception unusable in healthcare. Patient calls in Gujarati, Hindi, English or any combination are served consistently, with Surat-style code-mixing welcomed because that is how patients in the region actually speak.
Anaya is live as the hospital's inbound voice receptionist, integrated with the live on-premise HMS/CRM. Real-time doctor calendar reads, appointment write-backs, reschedule and cancel operations all flow through the live HMS API verified on 14 May 2026. The 15-stage architecture handles new-patient onboarding (name and age capture), OLD-patient recognition (auto-fill from /crm/patient response), and the full booking / reschedule / cancel / lookup workflow inside a single inbound conversation. The agent's BASE-vs-STAGE prompt split eliminates the most common voice-AI failure modes — re-asking captured fields, guardrail leakage into spoken audio, looping — which are the failure modes that previously made automated reception unusable in healthcare. Patient calls in Gujarati, Hindi, English or any combination are served consistently, with Surat-style code-mixing welcomed because that is how patients in the region actually speak.
Before Caller Digital
Peak-hour inbound calls dropped due to limited reception capacity
Rescheduling required reception to switch between HMS and the live caller
After-hours appointment booking was not served
Gujarati-Hindi-English code-mixing handled inconsistently by reception staff
Lookup-style calls ("when is my appointment?") consumed disproportionate reception time
Cancel and reschedule flows lacked structured identity-verification
After Caller Digital
Inbound calls served continuously by Anaya, integrated with the live HMS
Real-time doctor calendar fetch + booking write-back inside the call
After-hours and weekend booking handled without reception staffing
Gujarati-default trilingual conversation with Surat-style code-mixing
Privacy-gated appointment lookup with phone read-back verification
Cancel and reschedule with explicit "haan/yes" confirmation gates
Benefits of Integration
Read More Case Studies
Frequently Asked Questions
An inbound voice AI receptionist (Anaya) for appointment booking, rescheduling, cancellation, appointment lookup and patient FAQ — covering all 9 specialty departments at NuFace Maxillofacial & Dental Hospital, integrated with the hospital's on-premise HMS/CRM via secure API access.
Gujarati (default), Hindi and English, with natural Ahmedabad/Surat-style code-mixing welcomed because that is how patients in the region actually speak. The agent greets in Gujarati and from the second turn onward switches silently to whichever language the caller is comfortable in.
Anaya integrates with the NuFace on-premise HMS/CRM via secure API access (with VPN or required network access provided by the hospital) to (a) read doctor calendars and slot availability in real time, (b) classify the caller as NEW or OLD via phone number on /crm/patient, (c) create, update, lookup and cancel patient appointment records, and (d) trigger SMS/WhatsApp confirmations via the hospital's existing integrated workflow.
After phone number capture and digit-by-digit read-back, Anaya calls /crm/patient. If the patient is OLD, the response auto-fills name, age and city — Anaya never asks for them again. If the patient is NEW, Anaya captures name and age in the BookingPatientInfo stage. A dedicated update_known_data tool lets the patient correct any field mid-call without restarting the conversation.
Anaya's instructions are split into two layers. The BASE layer is sent once at session start and contains the persona, voice, language and accent rules, conversational guardrails, objection handling, and full hospital reference information. The STAGE layer is pushed at every state transition and contains the current stage name, a snapshot of everything captured so far, and a single-sentence task for the model plus the tool to call next. This split eliminates the most common voice-AI failure modes — re-asking captured fields, guardrail leakage into spoken audio, looping on stale instructions — which previously made automated reception unusable in healthcare.
Start Automating Calls Today
Unlock 24/7 multilingual AI voice agents for sales, support, & operations.
© 2025 Caller Digital | All Rights Reserved