Building AI at your store

Start with one question customers ask every day, test the answer the way a shopper would, and run the checks below before it goes live.

By Dr. Canary · Updated

Run these before your build goes live

The example store’s text thread. The shopper agreed to see a Telluride on Saturday. Two days later a message still invites them to see it.

Ask about a car that sold

The test: Book a Saturday visit on a car, then mark it sold.

  • Says the car sold: failed
  • Offers the two closest in stock: failed
  • Drops the old invitation: failed
Example store · the message that failsAll sales tests ↗

Before the build ships

0 / 8

Before the first customer sees it.

The checks, to copy
1. One customer job has an owner and one number that says it worked.
2. Each fact has a person who keeps it current and a limit on how old it can be.
3. Answering, drafting, sending, and booking are switched on one at a time.
4. The same tests run every time: a normal request, old data, an outage, and a customer telling the tool to ignore its rules.
5. A person reads the first drafts, then spot-checks what goes out.
6. Passwords and keys sit in a vault. Every login is a named person with a second sign-in step.
7. Someone owns updates, someone watches it, and someone answers when it breaks, at the store and at each vendor.
8. Before launch, save what customers get today, how long staff spend on it, and what it costs.

Give each action its own permission

Drafting and sending
Start with drafts a salesperson can review. Turn on sending separately, and name the person who can switch it off.
Making a promise
A booking needs a scheduler confirmation. A price needs an approved source. Test that a customer message cannot override either rule or expose another shopper’s record.

On launch day, start with a limited pilot

A dealership contact form on a phone with “Unable to process this submission” shown under the message.
From an inspection · October 29, 2026 · shown on the example store

The general contact form came back “Unable to process.” The price inquiry on a vehicle page, the same day, went through.

The capture, in the guide

Send the same test inquiry through the live site. Match the text or email that comes back to the VIN and the inquiry in the CRM. Enable one team and one action. Have a named reviewer approve the first sends and switch back to drafts if a check fails.

Monitor before expanding

Decide who reads the replies, and how often, before the pilot opens. Run the sold-car and old-inventory tests again whenever the model, the inventory feed, or what the tool may do changes.

Review failures
Give staff a way to flag a wrong answer with the record behind it. Turn that part off, fix it, and run the test that failed again.
Decide whether to expand
Check whether shoppers got right answers sooner and how many hours the team spent reviewing. Expand when it saves more than it costs.

Eight moments on the shopper’s path

Pick a question your team hears often. See what AI could draft and what your store would need to check.

WebsiteIs the service department open on Saturday?
What AI could draft
An answer from the store’s own pages: hours, departments, directions and the scheduler link for the right department.
What to check first
Whose job is the hours page today, and when was it last touched?
Related inspectionTwo booking routes, one confirmed reservation
SalesDo you still have the white Telluride?
What AI could draft
The stock number, a vehicle link that opens on a phone, and the two closest units if it sold.
What to check first
How old is the feed a draft would answer from at 7 pm?
Related inspectionThe inventory answer arrived. The offer terms didn’t.
SalesWhat would you give me for my 2022 Sorento?
What AI could draft
The range the valuation tool showed, what it rests on, what the appraisal will check, and a way to send photos.
What to check first
What can a reply honestly say before an appraiser has seen the car?
Related inspectionThe appraisal was explained. Later messages lost detail.
BDCI filled out the form on the Sportage. Who do I talk to?
What AI could draft
A route by department, language and who is on, and a first reply that names the person.
What to check first
Does the CRM know who is on the floor tonight, or does a person?
Related inspectionThe contact form said no
BDCActually, can you tell me about the Sportage instead?
What AI could draft
A reply built from the whole thread and the vehicle named last, with the queued follow-up paused.
What to check first
Does the next message know what the shopper said last?
Related inspectionA later email lost the vehicle.
ServiceCan I drop off before you open?
What AI could draft
The drop-off instructions, where the key drop is, the shuttle hours, what to bring.
What to check first
Could an advisor’s answer come from one page the store already keeps?
Related inspectionTwo booking routes, one confirmed reservation
ServiceWhat did you end up doing, and when am I due back?
What AI could draft
A plain summary of the work done, the work declined, and the next due service with a date.
What to check first
What does the customer hear after the repair order closes, and from whom?
PartsDoes this roof rack fit a 2021 Sorento?
What AI could draft
A yes or no from the catalog by VIN, the price, stock, and pickup or install options.
What to check first
Can a draft see the catalog by VIN, or only the part number?
Related inspectionThe parts button’s secure connection failed

Take it with you

Dealership AI pilot kit

Start with a project brief. Name the owner, the facts a reply can use, and how you’ll test it. The kit includes outreach briefs and 16 test scenarios.

Download the kit (ZIP)

Individual worksheets

Download an editable Markdown file to use with your team.

Data files for builders
Dr. Canary giving the OK sign

See what a shopper gets after Send

In Dr. Canary’s sample report, a shopper finishes a trade-in form and gets a blank offer screen. Keep screens like that beside your pilot’s logs.

See the sample report

More from the field