The reason we take on work in Novena is that the businesses here tend to be sharper about what they want than the brief lets on. Voice AI agents for a Novena team almost always ends up looking different to voice AI agents for a downtown Auckland one.
AI phone agents - wired into a Novena workflow, not bolted on the side.
Our goal is to give Novena businesses a three-day weekend, so people can spend more time with their families and the people they love :)
What voice AI agents actually does
Never miss a call again. AI phone agents that answer common enquiries, book jobs, and route urgent ones - in a Kiwi voice your customers won't hate.
- 01 Trained on your business hours, services, and pricing
- 02 Books appointments straight into your calendar
- 03 Texts the team for anything urgent
- 04 Full call transcript and audio recorded for QA
Built on: Vapi Retell Twilio OpenAI Realtime
Without Kiwi Dynamics
With Kiwi Dynamics
What you actually get
Every engagement is scoped and quoted up front. This is what is in the box.
- A working pilot, in productionNot a prototype on someone's laptop. The first slice of voice AI agents runs against real work within weeks.
- Your data stays yoursIt runs on your accounts and your tools. If we part ways you keep the system and everything in it.
- The workflow mapped before codeWe write down what good looks like for Novena businesses first, so nobody is guessing at handover.
- Support after it landsThe people who built it stay reachable when the business changes shape around it.
How voice AI agents compares
The two things most businesses do instead, and where each one runs out.
| Hiring for it | An off-the-shelf tool | Kiwi Dynamics | |
|---|---|---|---|
| Fit to how you work | Fits perfectly, costs a salary | You bend your process to suit the tool | Built around the workflow you already run |
| Time to something useful | Immediate, and permanent | Quick to switch on, slow to make fit | A working slice in weeks, then hardened |
| Who owns the data | You do | The vendor, on the vendor's terms | You do, in your own accounts |
| When it breaks | That person sorts it, if they are in | A support queue and a ticket number | The people who built it |
| What it costs | A salary, every year, forever | Per seat, forever, used or not | Scoped and quoted up front |
The pattern across Novena engagements we've shipped.
- Novena is Singapore's medical hub, dense with private hospitals and specialist clinics - AI here means handling patient-facing and admin work with genuine care around accuracy.
- One of the highest concentrations of private hospitals and specialist medical centres in the region, serving both local patients and medical tourism. Clinics here want AI that reduces admin load without ever compromising on precision.
We work with teams across Novena: Novena Medical Centre · Thomson · Balestier · Toa Payoh · Newton.
Talk to us about this →
How we build voice AI agents for a Novena team.
We scope narrow, ship a working pilot, then harden it into production. The first slice is the highest-leverage workflow for your Novena business, so value lands before the build is finished. AI phone agents.
Talk to usHow the work runs
- Find the one workflowWe look for the job costing Novena businesses the most hours or the most leads, and deliberately ignore the rest for now.
- Ship a working sliceA narrow version goes into production in weeks, against real work, so the value shows up before the build is finished.
- Prove it, then widenWe measure it against what the work cost before. If it does not pay for itself, we say so rather than scaling it.
- Harden and hand overLogging, fallbacks and a real handover, so it keeps running when we are not in the room.
The outcome for Novena teams
The shape of the result for Novena teams: 42% of after-hours calls now booked without human input. Built on Vapi, hardened with the rest of the stack as it scales.
Not your typical AI agency.
Honest about what AI can and cannot do
Ships the one workflow that pays for itself
Hours given back, never the size of the invoice
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
FAQ
How fast could we have voice AI agents in production?
Eight to ten weeks for most Novena businesses. Faster if your data is in good shape and slower if we're untangling a legacy integration first. We'll give you a realistic number on the scoping call rather than the optimistic one.
What's the smallest engagement you'd take on?
A two-week paid discovery for Novena businesses that aren't sure whether the build is worth doing at all. You get a one-page write-up of what we'd build, what we'd skip, and what it would cost. About 30% of those discoveries end with us recommending you don't proceed.
Do you have proof this works for Novena businesses?
Direct case study: 42% of after-hours calls now booked without human input. Happy to walk you through full numbers on a call.
What if our Novena doesn't have any data ready?
Most don't. Getting the data into shape - ingestion, cleaning, the lightweight contracts you need before any model is useful - is part of the engagement. For voice AI agents specifically, we typically run that work on Vapi, Retell, Twilio, OpenAI Realtime and assume messy starting conditions from day one.
One short call.
Tell us what you're trying to fix. We'll come back inside a working day.
Talk to us about this
Tell us what you're trying to do and we'll reply with how we'd build it - no obligation.