AI Receptionist (Open Framework)
AI Receptionist (Open Framework), scoped to your business, delivered at a fixed price and run for you afterwards.
This is the outcome, not a promise of one
A worked example of exactly what this build does once it is live in your business.
- 14:02Call from +61 4** *** 219 rings out. Everyone is on a roof.
- 14:02Number checked: mobile, not a known spam range.
- 14:02SMS out: “Sorry we missed you, it’s Dan at Coastline.”
- 14:03Reply: “hot water system leaking, can someone come today”
- 14:03Dan paged. Job drafted with the transcript attached.
- 14:04Booked. Nobody touched a phone.
Outcomes
- The repetitive half of a job handled, the judgement half escalated
- Answers grounded in your documents rather than invented
- Every automated decision logged so you can read it back
Voice agent
Audio streams into transcription, a bounded language model decides what to say next, speech comes back, and the whole loop stays inside the latency a human conversation tolerates.
- Define the narrow job the agent may do and everything it must hand off
- Write the prompt, the refusals and the escalation triggers before any code
- Build an evaluation set from real recorded calls and score against it
- Run it on our own line before it ever answers one of yours
Four things that are true of every build
The terms are the same whether you spend two thousand dollars with us or twenty.
A fixed price
Quoted before we start, naming what it does and what it will not do. It does not move unless you change the scope in writing.
Proof before launch
You sign off on real output from your own cases, not a demo video. If it does not convince you, it does not go live.
Everything in your name
Accounts, numbers, data, repository. Nothing switches off if you stop working with us, and there is no migration to negotiate.
30 days of fixes free
Anything that does not behave the way we said it would gets fixed at our cost for the first 30 days, whether or not you take the managed plan.
What is in the box
The whole build, on one page. No line item appears later that is not here.
| Product line | Applied AI |
|---|---|
| Implementation pattern | Voice agent |
| Best fit | trades, clinics and any business that misses calls after hours |
| Runtimes available | python, javascript |
| Foundation | Built on LiveKit Agents, an Apache-2.0 framework with native telephony, so the agent is portable across phone providers rather than locked to one. — LiveKit Agents (Apache-2.0) |
| Platform services | Open frameworks running on infrastructure you control, a model provider of your choice, and an evaluation set built from your real cases. |
| Typical build | About one week to a staging number, then live monitoring before sign-off |
| Build price | ~$2,500 fixed scope |
| Run price | ~$390/mo managed, platform usage billed at cost |
| Compliance handled | Consent capture, sender identification, automatic opt-out, logging and retention |
Related builds
Same pattern or same product line.
AI Outbound Follow-Up Calls
Audio streams into transcription, a bounded language model decides what to say next, speech comes back, and the...
Assistant Access to Your Systems
An assistant is given a small set of explicitly defined, permission-scoped tools against your systems, and...
Call Summary into the Customer Record
Documents and photos come in, structured fields come out, and anything the model is not confident about is...
Get this built for your business
Fixed-price scope, about a week to a working staging number, and we run it afterwards if you want.