Hashlogics
← Case studies
Case study · Automotive Repair & Service Management · Toronto, Canada

ZhoopZhoop

The phone keeps working when the whole team is under a car.

AI receptionist and parts procurement for a multi-branch auto repair business.

ZhoopZhoop product interface
Client
ZhoopZhoop
Industry
Automotive Repair & Service Management
Region
Toronto, Canada
Engagement
B2B · multi-location auto repair · AI voice agents + WhatsApp assistant + admin dashboard
Overview

ZhoopZhoop answers the shop phone and works it. AI voice agents take inbound customer calls and book appointments, while outbound agents call suppliers to collect and compare parts quotes. A WhatsApp assistant handles the same booking work over chat. Staff see every call, transcript, quote, and appointment across all branches on one dashboard.

The challenge

The problem we set out to solve.

01

Staff stopped work to answer calls, so calls and bookings were missed.

02

Someone had to ring each supplier by hand to check parts and prices.

03

Supplier quotes had no central home, which slowed procurement decisions.

04

Phone and WhatsApp inquiries were handled inconsistently across branches.

What success needed to look like

  • Answer every customer call, even when every tech is on the tools.
  • Collect supplier quotes without staff working the phone.
  • Keep calls, quotes, and appointments visible across every branch.
Our approach

How we delivered it.

01

Diagnose

Traced where the shop lost time — unanswered customer calls on one side, manual supplier ringing on the other.

02

Design

Designed both agent flows: inbound answer to booking, and outbound supplier call to quote comparison.

03

Build

Built the FastAPI backend and React dashboard, then layered in Deepgram voice agents, Twilio routing, and the WhatsApp assistant.

04

Launch

Rolled out across multiple repair locations with role-based access for managers, front desk, and procurement.

05

Run

Tuned the agents against real call transcripts, with Sentry monitoring the live workflows.

The solution

What we built.

We built AI voice agents that work both directions. Inbound agents answer customer calls, collect booking details, and confirm appointments. Outbound agents call suppliers on request, gather parts availability and pricing, then hand back a comparison. Twilio routes the audio, Deepgram runs speech and turn-taking, and OpenAI handles reasoning and function calls. A WhatsApp assistant covers the same bookings over chat. Behind it, a FastAPI backend stores transcripts, call records, and AI summaries, and pushes live updates to the dashboard over WebSockets.

AI outbound supplier calling that collects parts availability and pricing
AI inbound receptionist that books appointments around the clock
WhatsApp AI booking assistant
Research and quote comparison across suppliers
Product and supplier management
Shop schedule and appointment booking
Call logs, transcripts, and recordings in one dashboard
Multi-location support with role-based admin
Shop dashboard with call volume, resolution time and booking metrics
Shop schedule and bookings calendar
How it’s built

Tech stack

React 19Vite 7TypeScriptTailwind CSSTanStack QueryZustandFullCalendarFastAPI (Python)SQLAlchemy + AlembicCelery + RedisWebSocketsPostgreSQLRedisAWSDockerNginxSentryGitLab CI

Integrations

  • Twilio Programmable Voice
  • Twilio WhatsApp Business API
  • Deepgram Voice Agent (speech-to-text, text-to-speech, turn-taking)
  • OpenAI Chat Completions (reasoning + function calling)
  • SendGrid
  • AWS S3
  • PyMuPDF (quote document parsing)

Roles & access

  • Shop manager
  • Front desk / reception staff
  • Procurement team
  • Customer (call or WhatsApp)

Security

  • JWT access tokens with HTTP-only refresh cookies
  • Role-based access control
  • Protected webhook endpoints, HTTPS-encrypted communication
  • Secure storage of call recordings and transcripts
  • Password hashing with bcrypt
More from the build
Auto Receptionist sign-in for shop staff
Customer profile sign-in that carries service history between shops
AI receptionist answering a live call on a laptop
The takeaway

A repair shop loses money on both phones — the one that rings and the one nobody has time to dial. We automated both.

Start

Let’s build the one that runs after.

A senior engineer reads every brief, and your call gets scheduled within 24 hours.

What happens next

  1. 01

    You send a brief or book a call

    Two minutes, whichever you prefer.

  2. 02

    A senior engineer replies within 24 hours

    Not a sales rep.

  3. 03

    Honest scoping, in writing

    And if we’re not the right fit, we say so.

Abdul Basit, CEO of Hashlogics

“I started Hashlogics because too many teams ship a demo, get paid, and disappear. We build to a standard we’d run ourselves — and we stay to keep it running.”

Abdul Basit · CEO · a direct line

Not ready to talk? Take the checklist.

12 questions to ask any AI agency before you sign — the ones that separate a demo shop from a team that ships to production.

Get the checklist

Free · no newsletter