Skip to content
Features

Built for live patient calls, not demos

Named safeguards on every turn, confirm-to-book rules, calls logged with transcript and outcome, and team-reviewed go-live once forwarding is set and you go live.

Call control

Not one AI prompt. A state machine with named checks on every call.

Most AI phone tools let one instruction set run the whole call. Vgentive breaks each call into clear steps with a defined handler, fallback path, and logged outcome on every turn.

Typical AI phone tool

One instruction set

A single prompt tries to cover every caller need at once. The model improvises what happens next.

Unpredictable when the call gets complex

Vgentive

Clear steps per turn

Each call is broken into defined steps. The system decides what happens next, not free-form AI answers.

Every turn logged with a named outcome

What happens on a live call

Six defined phases. Each one has a handler, a fallback, and a logged outcome, not a guess from the language model.

  1. Step 01

    What does the caller need?

    The first words decide the path: question, booking, emergency, reminder reply, or handoff to staff. Each path follows its own steps, not an open chat.

    • Question
    • Booking
    • Emergency
    • Reminder reply
    • Staff handoff

  2. Step 02

    Facts from your setup only

    Timings, doctors, slots, and answers come from what you have set up. If nothing is found, the agent says so. It does not make up an answer.

  3. Step 03

    Caller must say yes

    Bookings and sensitive steps need a clear yes from the caller. The agent reads back doctor, time, and department from the booking system only.

  4. Step 04

    Call closes with a record

    Every ended call is logged on the Facility Desk with transcript and outcome. Built-in checks run throughout the call, not only at the end.

  5. Step 05

    Staff can take over anytime

    Live bridges follow your emergency rules and configured reception or inquiry numbers when callers ask for a person. If staff do not answer, callbacks land in the desk queue instead of looping.

  6. Step 06

    Outbound uses the same engine

    Reminders, re-engagement, and feedback calls follow the same safeguards as inbound, with outbound calling controlled from the Facility Desk.

Booking rules in practice

What the agent is allowed to say

Redacted call excerpt. System results are shown in brackets. The agent does not invent doctors or slots. It does not guess when a lookup fails.

Booking rules

  • Live lookups only

    Doctor names and appointment slots come from your schedule, never invented.

  • Clear when data is missing

    If a lookup fails, the agent says so and offers real alternatives from your roster.

  • Caller confirmation required

    Bookings are read back and confirmed only after an explicit yes from the caller.

  • System results drive speech

    Every factual line maps to a tool result, visible in the transcript as system events.

Built-in checks

Named safeguards, named

Each check is a small rule that runs during a live call. Below is a sample grouped by what each protects.

Boundaries

Built with limits, on purpose

A voice agent on a hospital line should know what it isn't. Here's what Vgentive refuses to do, by design.

  • No medical advice

    Symptoms go to a department or doctor. The agent never diagnoses, recommends medication, or suggests treatment.

  • No invented confirmations

    A booking is only confirmed after the booking system succeeds. If it fails, the agent says so and does not pretend the slot is set.

  • No invented facts

    If something is not in your knowledge base, the agent says it does not know and offers a callback. It never guesses to sound helpful.

  • No unsolicited outgoing calls

    Reminders and campaigns run only when outbound is on and a configured rule or staff action starts them. The agent never cold-calls patients on its own.

  • No silent failures

    If a call drops, stalls, or hits an error, it is logged and flagged on the desk. It is not marked as a clean, successful call.

  • No pretending it's human

    The agent identifies as your hospital or clinic voice assistant on the line. It does not claim to be clinical or front-desk staff.

  • No third-party disclosure

    It will not share another patient's appointment, diagnosis, or records with a caller, regardless of how the request is phrased.

  • No cross-facility data

    A branch agent never reads another facility's patients, schedule, or knowledge base, even under a shared group login.

  • No off-script promises

    The agent will not offer discounts, waivers, or clinical commitments that are not in your configured knowledge base.

These aren't gaps. They're the same discipline that makes the rest of the agent's behavior something you can trust on a real patient line.

Call types

Every call type

Outgoing calls run only while outbound calling is switched on for your facility. Appointment reminders queue on book or reschedule (lead time in Settings) or when staff tap Call now; feedback follows completed visits; and campaigns start when your team presses Start.

Inbound

  • Enquiry
  • Booking with confirm-to-book from your live schedule
  • Emergency bridge to staff, plus reception handoff when configured

Outbound

  • Appointment reminders on book or reschedule (lead time in Settings) or Call now. Outcomes on the call: confirmed, declined, callback requested, or no-answer. They do not auto-update the calendar.
  • Re-engagement campaigns from staff-built flows and authorized lists
  • Patient feedback calls with ratings logged on the Facility Desk
  • Staff-scheduled outbound for follow-up, missed visit, payment reminder, or custom

On the Facility Desk, staff-scheduled outbound appears under Patient Recall (marketing name: "Scheduled calls").

On every plan.

Facility Desk

Everything your team runs from one desk

Overview, callers, call logs, appointments, outbound, knowledge, users, and support tickets. Scoped to your account.

Home

  • Overview

    Calls, appointments, outcomes and credit use at a glance.

  • Credits

    Balance and full transaction ledger.

  • Billing

    Razorpay payment links and desk recharge where your role allows; onboarding payment and invoices.

People

  • Callers

    Directory with call history.

  • Patients

    Records linked to bookings and calls.

Reception

  • Call logs

    Search by caller, phone or transcript; filter by outcome, intent and date; recordings.

  • Enquiry and Emergency views

    Filtered views of your call logs.

  • Appointments

    Calendar, booking and completing visits.

  • Callbacks

    Queue with call now and resolved.

Re-engagement

  • Lists, People, Responses

    Flow builder with templates, CSV lists, branch and collect steps, and response export

Reminders and scheduled

  • Reminders

    Auto reminders on book or reschedule, Call now, and editable scripts. Log cancel or reschedule intent; staff update the calendar.

  • Scheduled calls

    Follow-up, missed visit, payment reminder or custom. On the Facility Desk, staff-scheduled outbound appears under Patient Recall (marketing name: "Scheduled calls").

Feedback

  • Patient feedback

    Your questions, ratings, comments and trends.

Catalog

  • Doctors

    Schedules, leave dates and fees.

  • Departments

    Manage the departments callers can book into.

  • Knowledge

    26 fact topics with AI drafts you review.

Access

  • Users and roles

    Custom roles from 60+ permissions; phone numbers masked unless a role allows them.

Facility and support

  • Settings

    Hours, emergency rules, voice and greeting, and switching call types on or off.

  • Support tickets

    Raise and track help requests.

  • Branch switcher

    Pro and Custom

    Switch between branches with one login

On every plan.

Knowledge base

25+ hospital fact topics. Not a document upload. Not a chatbot.

The agent only speaks from what you configure, structured by topic, not scraped from a PDF.

  • Scoped by topic

    Parking, fees, insurance, booking rules, teleconsult. Each fact type has its own field. The agent cannot answer what you haven't added.

  • Visibility by facility type

    An online-only clinic's agent won't invent ambulance or parking answers. Knowledge scope follows your operating mode.

  • Drafted in your language

    Knowledge entries are drafted by AI in your facility's language: Hindi for Hindi facilities, English for English. Your team reviews before it goes live.

Re-engagement

Design outbound call scripts in a visual flow editor. No code.

Pro and Custom

Starter templates, branch and collect steps, delays, and exportable responses. Built visually on the desk; your team presses Start.

Most outbound call tools give you a script field. Vgentive gives you a desk flow builder: starter templates, branch and collect steps, delays, and loop conditions, built visually and executed without free-form AI inference on scripted campaign calls.

Import people from CSV, author the flow, set the calling window and desired outcome, then press Start when your team is ready. Responses and outcomes export from the desk for ops review.

  • Visual branch editor

    If caller says yes, if no-answer, if declined.

  • Step delays and loop conditions

    Delays and loop conditions between attempts.

  • Starter templates

    Win-back, announcement, and consultation paths you tailor per campaign.

  • Scripted calls bypass LLM inference

    Faster, cheaper, more predictable on campaign steps.

Patient Experience

More than feedback calls. A full post-visit ops module.

Ratings, trends, volume audits, and queue-eligible bulk calling, not just a list of call outcomes.

  • Trends over time

    Rating trends and volume audit across any date range. See if patient satisfaction is improving week on week.

  • Poor-score alerts

    Low ratings are flagged automatically so your ops team can follow up before a bad review goes public.

  • Queue-eligible bulk actions

    Select completed visits in bulk and queue feedback calls in one action. No manual list management.

  • Outcome per call

    Every feedback call is logged with rating, comment, and call recording, tied back to the original appointment.

  • Department-level trends

    Filter satisfaction and volume by department or doctor on the Facility Desk.

  • Call recordings

    Download recordings from the Facility Desk.

Multi-branch

Multi-branch: one login, separate lines

Pro and Custom

Switch between branches with one login. Each branch has its own phone line, credit balance, and subdomain.

Starter includes 1 location. See pricing

  • Switch branches without logging out

    Pro and Custom admins move between locations from the Facility Desk branch switcher.

  • Separate phone line per branch

    Each branch keeps its own inbound number and forwarding path. Callers reach the site they expect.

  • Separate credit balance per branch

    Usage and top-ups stay scoped to the branch you are viewing. Finance can reconcile per site.

  • Branded subdomain per branch

    Staff sign in at your facility subdomain, for example sunrise.vgentive.com, not a generic login page.

  • Schedules and knowledge per branch

    Doctor rosters, departments, and knowledge follow the branch context. The agent does not mix sites.

  • Starter stays single-location

    Starter includes one location. Add branches when you move to Pro or Custom on pricing.

Choose your clinic voice

Staff hear a sample before go-live. Official speakers only. Number of voices depends on your plan.

See pricing

Reliability

Built for peak OPD hours, not quiet demo rooms.

Stall detection, barge-in control, and conflict warnings, because real clinics are noisy and busy.

  • Stall detection

    If the agent goes silent for ~9 seconds, it plays a check-in line instead of dead air. No caller ever sits in silence wondering if the call dropped.

  • Barge-in control

    Callers can interrupt the agent while it's speaking, but not during processing. No accidental cutoffs, no lost words.

  • Outbound conflict detection

    The desk warns your team before a reminder call, confirmation call, and scheduled follow-up all queue for the same patient on the same visit.

Set-up model

Every hospital or clinic runs on the same engine

Fast onboarding works because you change data, not code. The voice engine and built-in checks are shared. Your doctors, hours, and rules are yours alone.

Per facility

What changes per hospital or clinic

Loaded as your data and settings, with no custom code per site.

  • Doctors, departments, and bookable services
  • Hours, holidays, and slot rules
  • Knowledge checklist (parking, insurance, fees, custom facts)
  • Greeting, language setting, and clinic voice
  • Emergency acceptance and transfer rules
  • Incoming and outgoing call types per module

Shared platform

What never changes

The platform every site inherits on day one.

  • Voice engine and speech stack
  • Step-by-step call control and built-in checks on every turn
  • Booking chain: doctor schedule → slots → confirm
  • Safety fast-paths and refusal rules
  • Facility Desk modules and call records

Facility types

Built for the kind of facility you run

9 healthcare facility types on the same platform. Emergency options follow the facility type.

Emergency options follow the facility type. See healthcare overview · Solutions by facility type

Testing discipline

Built from real production calls

Every safeguard on this page exists because a real call surfaced the problem it solves. We do not ship call behaviour from a whiteboard alone.

  • Scenarios from real recordings

    70+ test scenarios come from anonymised hospital and clinic calls. They cover booking edge cases, emergency language, Hindi-English switches, and schedule mismatches.

  • Checks tied to observed failures

    When a live call exposes a gap, the fix becomes a named check with a replay scenario. It is not a one-off instruction tweak.

  • Language parity before release

    Hindi sites get Devanagari copy. English sites get English-only paths. Both are tested on the same scenarios before release.

  • Replay before every release

    Named checks are replayed against stored call scenarios before a build goes live. A failed replay blocks release until the fix is verified.

  • Flags visible in the Facility Desk

    When a safeguard fires on a live call, the flag name and outcome appear on the call record. Ops can filter and review without digging through raw logs.

  • Weekly review on real call logs

    Ops filter last week's outcomes on the Facility Desk, spot-check bookings and transfers, then update schedule or knowledge before Monday peak.

This is ongoing review from production calls and scenario replay. It is not a claim that every path runs in a fully automated test suite today.

Recently added

  • Voices you can hear

    Your facility gets a natural clinic voice from an official speaker list. Staff hear a sample before it goes live on the line. Unofficial speakers are not used.

  • Voice stays out of the long settings form

    Changing the speaker is a focused picker on the facility record, so the rest of hospital setup stays short.

  • Low-credit warning

    The Facility Desk shows a warning when a hospital is running low on credits, before calls are affected.

  • True Hindi on generated copy

    Knowledge drafts, campaign lines, reminder wording, and call summaries follow the hospital's language. Hindi facilities get proper Devanagari, not Latin Hinglish. Every scenario is tested in both Hindi and English before release.

  • Review flags on every call

    Calls that need review are flagged automatically with a named reason, visible on the Facility Desk before your team opens the transcript.

  • Credit history per call

    Every minute, transfer, and AI desk action is logged on the call record so finance and ops can review spend.

See it on your facility line

Start your free trial on the app, or book a demo to walk through inbound and outbound on the Facility Desk.

Start free trialSee pricing