Home / Case studies / Auto repair AI app
Case study · AI operations app

An AI operations app for auto repair shops

Now used by 28 auto repair shops, grown from 13 modules to 29, with AI running costs so small that all my heavy testing came to about 4 cents.

The problem

Auto repair shops run on small teams and full days. The people at the front desk and in the bays are good at fixing cars, not at writing messages or wrestling with software.

Retyping the same context

Every tool asked for the shop's name, address, hours and prices again, and still gave back generic results.

Slow customer communication

Reminders, follow-ups and messages about declined work were written from scratch, one channel at a time.

Diagnostics that are hard to explain

A mechanic's read on a misfire doesn't turn easily into words a customer understands and trusts.

Scattered tools

A different tab or login for every job, so good tools went unused.

What I built

A standalone web app that opens in any browser, with 29 modules across 4 categories: Customer Service, Tech & Repair, Inventory and Business Ops.

  • One shop profile behind everythingA shop enters its name, tagline, address, logo, staff and service prices once, and every module uses them.
  • Customer communicationPick a touchpoint, a customer and a service, and the app writes the SMS, the email and the phone script at once.
  • The Repair AssistantA technician enters the vehicle, symptoms and OBD codes, and gets likely causes, tests, parts, labor hour estimates and a plain-language script for the customer.
  • Running the shopParts inventory with recall alerts, a light customer database, an SOP manager, a history of everything generated and an in-app AI assistant.

Built with: WordPress, Supabase sign-in, Gemini and Claude (chosen per module).

How it works

Step by step

  1. Context once. The shop fills in its profile and price list one time.
  2. A short form, not a blank prompt box. Staff pick what they need and fill in a few fields.
  3. The right model for the job. Each module goes to Gemini or Claude, whichever suits that task.
  4. Refine in plain words. A refine bar under every result takes requests like "make it longer".
Results

What changed

28 shopsuse the app, and it has improved the systems within each one.
13 → 29modules, grown across four categories since launch.
1 requestgives an SMS, an email and a phone script.
~4 centsof API spend for all my heavy testing. AI running costs are close to zero.
See it in action

Inside the build

Watch the 4-minute walkthrough▶ Watch the 4-minute walkthrough
PLACEHOLDER: screenshot
Dashboard, dark mode, branding removed
Dashboard, dark mode, branding removed
PLACEHOLDER: screenshot
Shop profile editor, product name and client details redacted
Shop profile editor, product name and client details redacted
PLACEHOLDER: screenshot
One request, every channel (phone script, SMS, email), shop name and phone redacted
One request, every channel (phone script, SMS, email), shop name and phone redacted
PLACEHOLDER: screenshot
Repair Assistant advisor script
Repair Assistant advisor script
The question I keep in front of me is simple: what would make a busy team actually use this on a full day? Where does your team type the same context every single day?Christine Mendoza, Founder
Book a call with Christine

Tell me what your team keeps doing by hand.

A 30-minute call with me, not a sales team. I'll ask why your business exists, what's getting in the way and what you want, and tell you honestly whether a system would help.