AI calling system case study

Live callReply 0.8 s

Caller

AI agent

Human agent

AI calling system: illustration of the productbot.simulincs.com

ClientOwn product · deployed with outbound call centers

IndustryCall centers

ProductVoice AI + telephony

RoleFounder & solution architect

A real call, start to finishAuto insurance · 1:07 · ended in a transfer to a human agent

Recorded on our own line, unedited. The agent qualifies the driver, then hands the call to a person — which is what the product is for. The other voice is ours: we do not publish recordings of other people.

[ 01 / 07 ] About the client

Who it’s for

Outbound call centers run lead-generation and live-transfer campaigns for insurance, solar and Medicare, with rows of agents repeating the same qualifying script thousands of times a day. The AI agent is deployed with call-center clients and takes those calls on their own dialers.

[ 02 / 07 ] The challenge

What needed to change

Headcount and turnover cap how many calls a center can make. Cold leads hang up the moment something sounds robotic, so reply speed and handling interruptions matter enormously. And most call centers won’t give up the dialer they already use.

[ 03 / 07 ] The build

What we built

[01]
An AI agent that follows a campaign script on a normal phone line: it asks the qualifying questions, handles objections and never quotes a price
[02]
A plug-in for the center’s existing dialer: their dialer places the call and the AI takes it, with any phone carrier
[03]
Two campaign types: lead generation, where qualified leads are captured for the client’s team, and live transfer, where willing callers are passed to a human agent in the middle of the call
[04]
Natural turn-taking: the caller can interrupt, and the AI checks in if the line goes quiet
[05]
Pre-recorded script lines for the fixed parts of the script, which roughly halves voice costs; compliance disclaimers read word for word
[06]
A record of every call: recording, transcript, reply times, cost and outcome
[07]
Results pushed to the client’s CRM or dialer automatically, with retries
[08]
Do-not-call suppression, per-client line limits and a multi-client console with reports

[ 04 / 07 ] How it works

How it works, step by step

[01]
The center’s dialer calls a lead
[02]
Live audio streams to the AI agent
[03]
It listens and replies from the campaign script
[04]
Qualified leads go live to a human, or to the client’s lead list
[05]
The outcome is posted back to the client’s system

[ 05 / 07 ] Results

Results so far

0.8 s

median AI reply time on real phone calls

100+

simultaneous calls

20+

human, emotional AI voices

[ 06 / 07 ] Key decisions

Decisions that mattered

[01]
Keep the client’s dialer. Their dialer dials and our AI answers, so there’s nothing new for the team to learn.
[02]
Tap the audio at the phone switch rather than through one carrier, so any carrier works.
[03]
Pre-record the repeated lines to cut voice costs, and keep listening tuned for speed.

[ 07 / 07 ] Under the hood

The technology

VICIdial / AsteriskPython + FastAPI (asyncio)Real-time speech-to-text, LLM and text-to-speechSupabaseReact consoleDocker on Hetzner

For anyone curious about the tools. You don’t need to know any of this to work with us.

[ More work ] Keep reading

More case studies

View all work»

An AI phone agent that plugs into a call center’s own dialer

Who it’s for

What needed to change

What we built

How it works, step by step

Results so far

Decisions that mattered

The technology

More case studies

Have something to build?

Product build

Ongoing partner

Add AI to your business