Eterna Creative
Zonik AI

Case study · Application

Zonik AI is a logistics product we co-founded.

n8n to custom appAI voice agentslogisticsops automation

From n8n load tracking to a custom app that calls the driver when data goes dark

We shipped a Dispatcher + Worker loop on n8n, then transferred the full system into a custom application: self-scheduling load checks, VAPI voice check-ins, and a human exception queue when the automation cannot close the issue.

Client

Zonik AI

Solution

Custom app (from n8n)

Time to launch

May 2026 → ongoing

With first users
Beta
Tightest check interval
5 min
Human exceptions
1 queue

Overview

n8n to find the contract, then a custom app to run it

Check intervals, risk rules, and call holds started as n8n knobs - easy to tune and replay. When volume and the need for an owned runtime outgrew the canvas, we transferred the full loop into a custom application with the same contract.

Challenge

Load tracking never sleeps

Someone has to watch GPS, spot late ETAs, and call drivers - including at 3am. Fleets add night shifts or stretch dispatchers too thin. Both scale headcount with the fleet.

Our side

  • Dispatcher / Worker architecture
  • n8n prototype + call result contract
  • Full transfer from n8n into a custom application
  • Monitoring and on-call for the system

Partner side

  • Partner-led sales and operator relationships
  • Fleet driver, truck, and load data

Solution

Dispatcher + Worker, self-scheduling each load

The Dispatcher wakes on a schedule and only pulls loads due for a check. The Worker evaluates one load - GPS, ETA, severity - then writes its own next check time. Quiet loads go quiet. At-risk loads get tight intervals and, when needed, an AI voice call via VAPI.

Features

  • Self-scheduling triage

    Each load carries its next-check time. Cost follows risk, not fleet size.

  • AI voice check-ins (VAPI)

    When data cannot explain a delay, the system puts a voice agent on the phone and gets a structured reason back.

  • Call hold + force-call

    No repeat calls after a clean answer. Dispatchers can force contact when they need it now.

  • Exception queue

    Unresolved loads flip to needs-dispatcher. Humans work the queue - not every truck on the board.

Before → after

Before

Manual ELD checks, thin night coverage, problems found late. More trucks meant more monitoring hours.

After

The custom app is built to run continuously. Loads self-schedule. Drivers get called when data breaks. Dispatchers only see exceptions. n8n was how we learned the loop.

I don't want people sitting on GPS all night.

Nenad Stevanovic

Co-founder, Zonik AI

Free tool

Have an idea in mind? Try our product cost calculator

Instant results · 100% free · Takes ~3 minutes

Open calculator

Impact

What changed after launch

  • Beta

    With first users

  • 5 min

    Tightest check interval

  • 1 queue

    Human exceptions

  • Built for overnight and weekend tracking without a night shift
  • Driver contact on the system's schedule
  • Structured call results - not just audio to review later
  • Execution cost tied to risk, not fleet size
  • Dispatchers work a filtered exception queue

Results

The loop now runs as a custom application in beta with Zonik's first users: triage, evaluation, VAPI contact, write-back, and escalation. It started as a full n8n Dispatcher + Worker system. n8n Cloud billed per execution; volume made the canvas the bottleneck. We transferred the whole workflow into owned code - same contract, not a JSON dump.

Technologies

  • CA

    Custom application

  • N(

    n8n (original orchestrator)

  • VA

    VAPI

  • TW

    Twilio

  • Xano

  • PO

    PostgreSQL

  • OpenAI

  • SE

    Sentry

If your team is doing this by phone, start on n8n - finish in an app when the canvas breaks

Watch state, contact a human when data stops making sense, extract structure, escalate the rest. We map the lightest version first. Book a free 30-minute strategy call and we will say whether that is a workflow or a product.

Book free strategy call
I don't want people sitting on GPS all night. It watches the loads, calls the driver if something's wrong, and we only get what it can't finish.

Nenad Stevanovic

Co-founder, Zonik AI

Bring the bottleneck.

Book a free 30-minute strategy call. We'll map the lightest next step - whether we work together or not.

Book free strategy call

For AI agents