Scenario · Auto repair shop
AI receptionist for auto repair shops.
An AI receptionist for an auto repair shop reads the quote, booking and status enquiries that arrive while the advisor is under a hood, collects the facts an estimate needs, and drafts the reply from your own service list. One AI employee costs $149 a month on the Starter plan, and the estimate stays with the shop.
It runs over text: a form or quiz posts to the lead endpoint and the enquiry is stored before anything else happens. During the October tire rush the drafts queue up in batches of five every fifteen minutes and wait for the counter to open. Phone answering is custom scope on an Enterprise plan.
Unistaff · Auto shop
Counter
What arrives at this desk
The mix below is the deployment shape this scenario is written around. The timing column is the reason the work slips: most of it lands while the room is busy or after everyone has gone home.
“How much for brakes on a 2018 Civic?”
Anytime
Booking a drop-off
Evenings
Winter tire changeover and storage
October, November
Safety and out-of-province inspections
Anytime
“Is my car ready?”
Weekday afternoons
Warranty and work you did last month
Anytime
Towing and after-hours key drop
Nights
A small business asking about its vans
Weekday mornings
What it takes on, what stays with a person
Read the person column as the job that remains, and staff for that job rather than for the whole desk. Every row matches what the platform does today.
| Task | AI employee | Person |
|---|---|---|
| A quote request | AI employeeCollects what a quote needs — year, make, model, plate or VIN, mileage, the symptom and when it started — and reads it back | PersonPrices the job |
| Booking a drop-off | AI employeeDrafts the reply with your intake window, the key-drop rule and the inspection fee as you wrote it | PersonPuts the car in the bay schedule |
| A number in the first reply | AI employeeMarks every price as pending your approval; a draft that states one without the marker is rejected in code | PersonConfirms the estimate |
| Seasonal work — changeover, storage, inspections | AI employeeAnswers from the service list and collects tire size, storage and timing | PersonDecides capacity for the week |
| “Is my car ready?” | AI employeeStops. A car in the bay is a person's answer | PersonAnswers with the state of the job |
| Warranty and comebacks | AI employeeStops and hands over the history the customer gave | PersonThe advisor answers |
| The week's enquiries | AI employeeJournals every run with its inputs, outcome and error text | PersonReads the journal and fixes the brief |
Where it stops
The estimate itself, the diagnosis, parts availability, the promise of a completion time, and anything about a car already in the bay.
What the owner keeps
The estimate, the diagnosis and the bay schedule.
What a quote needs before anyone can price it
Most quote requests arrive missing half of this, and the back-and-forth costs a day. The first draft asks for what is missing and reads back what already came in.
Year, make, model and trim
Parts and labour times differ across a single model year.
Plate or VIN
The exact build, engine and options behind the estimate.
Mileage
Service intervals and what is likely worn.
The symptom, in the customer's own words
A noise described first-hand narrows the diagnosis.
When it started and whether it changed
A sudden change and a slow one point at different repairs.
Whether the car is drivable
Decides between a drive-in and a tow, which changes the day.
What was done last, and where
Warranty, comebacks and parts already on the car.
The answers arrive as structured fields alongside the enquiry, so the advisor opens one record instead of a thread.
Phone calls, honestly
Most pages selling an AI receptionist put a phone number in the hero. Text intake is what runs here today: a form or quiz posts to the lead endpoint, the enquiry is stored, and one email notification goes out with a five-second timeout — the enquiry reaches the database first, so a mail failure costs a log line while the record stays.
Voice is custom scope. The published plans are Starter at $149 a month, Scale at $599, and Enterprise at custom pricing; custom roles and custom workflows appear on the Enterprise column of the price table only. A voice desk starts as a scoping conversation about telephony, recording consent and who answers when the role stops.
The practical read: if most of your enquiries already arrive in writing, a text-first desk covers the volume today. If the desk lives on the phone, the first step is moving the repeat questions to a text channel and measuring what is left.
Web form and quiz intake
LiveThe enquiry is stored on submit, and the first reply is drafted on the next run.
Lead notification by email
LiveOne attempt with a five-second timeout; the outcome is logged either way.
Phone answering (voice)
Custom scope · EnterpriseCustom roles and custom workflows appear on the Enterprise column of the price table. A voice desk starts with telephony, recording consent and the handover rule.
Calendar booking
Scoped per deploymentNo calendar connector ships today, so live availability is scoped before launch.
SMS and messenger intake
Scoped per deploymentNo SMS or messenger connector ships today; the provider is chosen with you.
Full connector list with its evidence: /integrations
What it costs against the hours
The table is the site’s cost model run on this scenario. Twenty hours a week is the counter-and-phone share of an advisor's week, and the 50% share is the conservative read: every estimate ends with a person.
Read it as a comparison of hours. The share left over is the part of the desk that carries judgement — the exception, the upset customer, the decision — and it still needs a person. What changes is that the person spends the shift on those hours instead of retyping the same answers.
Model, except the price. Hours and share are assumptions; $149 is published
The brief this desk writes
Setup is a writing job. The role reads this material on every run, so the quality of the brief sets the quality of the drafts. An afternoon covers the first version, and the shadow week corrects it.
The service list with what each job depends on, and your inspection fee.
The seven facts a quote needs, in the order you want them asked.
Intake hours, the key-drop rule, the shuttle or loaner policy.
Seasonal work: changeover windows, storage terms, what an inspection covers.
The stop rules: estimates, diagnoses, completion times and any car in the bay.
Week one runs in shadow: every draft is read before it goes, and the material is corrected wherever the draft was wrong. At the end of it you have the share of drafts that went out unedited, which decides how much of the desk moves across next.
Questions people ask before they buy
Only your price, and only marked as pending your approval. The rule is enforced by a validator rather than by a prompt: a draft carrying a currency figure without the pending marker is rejected before anyone sees it. The advisor confirms the number and sends.
On Unistaff, no. Text intake runs today — a form or quiz posts to the lead endpoint and the first reply is drafted on the next run. A voice front desk is custom scope on an Enterprise plan and starts with telephony, recording consent and the handover rule.
That answer stays with the shop. A car in the bay has a state only a person knows, so status questions are a stop rule: the draft hands the message over instead of guessing.
The enquiries are stored as they arrive and the timer works through them in batches of five every fifteen minutes, so the drafts are queued before the counter opens. The shop decides capacity; the role collects tire size, storage and timing so the decision takes a minute.
One AI employee is $149 a month on Starter, with a 14-day pilot and cancellation at any time. The price follows the number of AI employees rather than the number of bays or advisors: $599 a month on Scale covers up to five.
Same machinery, different material. A fleet enquiry is qualified against whatever you wrote about fleet terms — vehicle count, service intervals, invoicing — and the draft ends with the concrete next step you set.
The same desk, another room
01
Coffee shop
The desk is a phone on the bar and an inbox nobody owns. Catering and hire enquiries arrive during the morning rush and get answered after close.
02
Salon or barbershop
Bookings and quote questions arrive while every chair is full. The reply that wins the booking is the one that goes out first.
03
Dental practice
The desk is with a patient, the phone is ringing and the inbox holds new-patient enquiries that decide next quarter's schedule.
05
Medical clinic
One person covers phones, check-in and scheduling. Requests that arrive during a consultation wait for a gap that never comes.
All five scenarios on one page: /resources/ai-front-desk