How does an auto dealer / service shop use intusell? A daily operations guide

In the first article, you trained the intusell AI: you uploaded your vehicle stock list, your trim and price information, your service offerings, and your FAQs to the knowledge base, marked your sales conversations, and configured the persona and response rules. Training was a one-time setup. Now the real work begins: how does an auto dealer / service shop use intusell — that is, how does an automotive business's day-to-day use of intusell actually work? This article walks through, step by step, what the assistant you trained does in the field over a full workday — from a stock question on WhatsApp to a test drive, from a service reservation to follow-up and handing off to a human.

This article is the second part of the automotive section of our sector-by-sector "how to train your AI" series. The first part, how to train the intusell AI, covered the setup; this one covers turning that setup into daily operations.

Quick answer

A day in the flow

The typical day of a dealership or service shop that has set up intusell is very different from before. In the old days, an advisor would come in each morning and go through dozens of unread WhatsApp messages and unanswered DMs one by one; "is this car available," "what's the mileage," "when can I come in for service" questions flowed in scattered all day. Now, the messages that came in overnight are already answered, leads are categorized, and some test-drive bookings are already made. The backbone of a day works like this:

The team is now occupied not with scanning messages but with conversations that genuinely require a decision — negotiation, inspection, closing the sale.

Who is it for?

This usage model especially makes sense for automotive businesses that:

• Receive heavy vehicle questions via WhatsApp and Instagram — dealers who can't keep up with dozens of "is this available, what's the mileage, what's your best price?" messages a day.
• Lose after-hours demand — dealerships and service shops that miss customers because they respond late to questions coming in the evening, on weekends, and during holidays.
• Manage service bookings by phone — workshops drowning in phone traffic during periodic maintenance, breakdowns, and the tire-change season.
• Manage many channels with a small team — businesses forced to track WhatsApp, DMs, listing-site messages, and the phone separately.

If you have a volume of demand that a single advisor can't keep up with, intusell works like a senior salesperson who meets that demand — not like a chatbot.

Incoming request: the customer asks about a vehicle, the AI recommends a suitable one

The flow starts when the customer sends a message. Imagine someone writes via WhatsApp: "I have a budget of 150k, I'm looking for an automatic sedan." The AI reads this message, scans the stock list and vehicle descriptions in your knowledge base, recommends vehicles that fit the customer's budget and need, and, if they're interested, directs them to the test-drive step.

An important point: the AI responds in whatever language the customer writes in. For dealerships selling abroad or serving tourists, this is critical — a stock question that comes in English gets an English reply, with no extra configuration needed.

If you added the "clarify the need before recommending" response rule during training, the AI first asks about budget, transmission type, fuel, and intended use. Thanks to this rule, the recommendation isn't random; it's based on the customer's real need. We separately explain how all these channels come together in a single inbox in the Instagram and WhatsApp automation article.

Stock, price, and service questions: answered from the knowledge base

In automotive, most incoming messages aren't a new buyer but recurring operational questions: "Is this car still available?", "What's the mileage?", "Any accident history?", "When can I come in for service?" These questions cycle in the same pattern throughout the day and eat up the advisor's time. intusell takes on this load by answering from the knowledge base.

The most critical rule here: the AI does not invent price or stock. It answers only from the source you uploaded to your knowledge base:

If information that isn't in the knowledge base is requested — for example, the live status of a car you didn't upload or a hard figure that's open to negotiation — the AI, instead of inventing information, says it doesn't know and suggests connecting the customer to an advisor. This behavior prevents you from giving the customer wrong stock or price information and then having to correct it; this is the foundation of trust. In a high-value decision like buying a car, the "I won't give you wrong information" trust comes before everything else.

You'll find a detailed account of this engine — automatically answering everything from service appointments to vehicle and quote inquiries with the knowledge base — in the service appointment automation article.

How the knowledge base is fed and stays up to date

The AI answering correctly depends entirely on how current your knowledge base is. intusell feeds the knowledge base from several sources and indexes all of them for pgvector-based search (RAG):

• Stock list: Uploaded as PDF, Excel, or CSV; make, model, year, mileage, trim, and price information come from here.
• Web URL: You provide the address of your dealership listing page, your service offerings page, or your warranty/trade-in FAQ page; the content is fetched and indexed.
• Free text: You type notes like "the campaign on brand-new vehicles applies this month" directly into the panel.

Vehicle stock and price are a frequently changing area; a sold car drops off the list within a few hours. That's why you refresh the knowledge base when you update your stock. The AI always speaks according to the latest source you uploaded — if the source isn't current, the AI won't be either, which is why stock freshness is the backbone of operations.

An additional safety layer: the AI is constrained by a sector-specific system instruction so it isn't prone to inventing things in the first place; on top of that, a protective layer scans the responses and flags risky statements. This layer runs in observe (shadow) mode by default — meaning it doesn't impose a hard block; it detects and flags, while the real control over behavior lives in the sector-specific system instruction.

Recovering the lead: proactive follow-up and CRM

In automotive, most sales dissolve among customers who ask about price, say "let me think about it," and disappear, or who postpone the test drive. intusell doesn't forget these leads. Interested customers who get information and then go quiet receive a proactive follow-up message; the lead is kept alive. Every conversation is logged into the CRM, so the customer's history, which car they were interested in, their budget, and what stage they're at stay on record — the next contact starts from where it left off, not from scratch.

Here a boundary needs to be clear: intusell does not maintain a managed "waiting list." What it does is offer an opportunistic re-offer to eligible WhatsApp customers in follow-up — for example, a reminder in the tone of "The car you asked about is still available, shall we set a good day for a test drive?" to a customer who was interested and then went quiet. On the service side, an opportunistic reminder goes to a customer whose periodic maintenance is coming due, with the same logic. This way, when you sit down to operations in the morning, it's clear which lead is hot and which is awaiting follow-up. You don't need to keep a manual reminder list.

Appointment and reservation flow: service and test drives

The backbone of automotive comes together in two kinds of appointments: a test drive for the customer who wants to buy a car, and a service appointment for the existing owner. intusell's universal appointment engine works with the same logic for both.

The AI doesn't give times off the top of its head; it looks at the working hours and busy slots you defined during training, and if it finds a suitable slot, it creates the appointment. For a service appointment, the customer shares the vehicle details (make, model, mileage) and the issue; for a test drive, the car of interest and a suitable time are confirmed. For each appointment, an automatic reminder (for example, 1 day and 2 hours before) goes out; this reduces the no-show — the missed appointment — that is costly in automotive. The customer manages their appointment themselves via a /manage-appointment/{token} link — cancellation or rescheduling is done in one click. Appointments are copied one-way to Google Calendar (intusell → Calendar); the advisor and service team see them in their own calendar. This module can be enabled on any plan; if you don't need it, you simply don't use it.

Handing off to a human: lock modes

You decide how autonomously the AI works. There are three lock modes:

In hybrid mode, the AI hands off a price question that's open to negotiation, a trade-in valuation, or an off-knowledge-base request to an advisor. At the moment of handoff, the full history of the conversation is in front of the team; the customer doesn't have to explain from scratch. You can change the mode at any time — for example, ai_only on a campaign day, human_only in a sensitive trade-in/negotiation flow.

One additional note: when a customer sends a file like a registration photo, a damage image, or a service invoice, that alone is not a reason to hand off to a human. The AI receives the attachment, understands the context, and continues the flow; it only escalates if there genuinely is a situation that requires a decision.

Reports: what's working, what to fix?

For operations to be visible, you track basic metrics in the panel. How many messages came from which channel, how many were answered by the AI, how many were handed off to an advisor, which models are asked about most, which service is busiest — seeing these serves two purposes:

1. Finding knowledge base gaps: If there's a topic the AI frequently says "I don't know" about and hands off, that information is missing from the knowledge base; once you add it, the handoff rate drops.
2. Improving response rules: You review the tags and correct misclassified conversations; the AI learns from these corrections. If you wish, you compare two different response approaches with an A/B test.

So reports aren't just a summary, they're the feedback loop for sharpening the assistant over time.

What it isn't

To place intusell in the right category, let's clarify what it isn't:

• It's not a chatbot. It's not a flow bot that answers from preset templates; it's a fully autonomous AI sales assistant that works with the knowledge and sales techniques you trained.
• It's not a listing site / vehicle marketplace. It doesn't replace your dealership; it directs to your stock list and your sales process, and the seller is the business.
• It's not a stock and price source. It doesn't invent information; it speaks only from the source you provide, says what it doesn't know, and hands off.
• It's not an automotive-specific priced product. The pricing model is based on messages and voice minutes; it doesn't change by sector. Modules can be enabled on any plan.

One more note: Instagram comment automation is rolled out gradually depending on Meta approval; the first step is always the approved WhatsApp and Instagram DM. So you don't start with the wrong expectation, let these boundaries be clear from the outset. For product and pricing details, see the solutions and pricing pages.

Frequently asked questions

Does the AI sell a car on its own?

The AI recommends a suitable car, answers the customer's stock and spec questions from the knowledge base, and takes them up to a test-drive booking. The sale itself — negotiation, inspection, contract, payment — stays at the dealership. In risky or off-knowledge-base situations, the AI hands the conversation off to an advisor. The final say always rests with the business.

Does the AI invent prices and stock?

No. The AI states a vehicle's price, mileage, and stock status only from the source you uploaded to your knowledge base. It does not invent a car, a trim, or live stock it doesn't know; it says it doesn't know and hands off to an advisor. This is the most important trust rule.

How does it book a service appointment?

The AI doesn't give times off the top of its head; it looks at the working hours and busy slots you defined, and if it finds a suitable time it creates the service appointment. The customer shares the vehicle details and the issue, an automatic reminder goes out before the appointment, and the customer manages it themselves via a /manage-appointment/ link.

Can a customer be connected to a human?

Yes. In hybrid mode the AI runs the normal flow and escalates the conversation to an advisor when needed. In human_only mode all conversations go straight to the team, and in ai_only mode the AI handles everything. You can change the mode at any time.

What happens to a message that comes in at night?

The AI responds 24/7. A "is this car still available?" question that arrives at 23:00 gets an answer from the knowledge base within seconds; when appropriate, it directs the customer to a test-drive booking. When you open up in the morning, ready leads and answered questions are waiting for you.

Which channels does it bring into a single inbox?

WhatsApp, Instagram DM, Facebook Messenger, Telegram, web chat, and email come together in a single inbox. Instagram comment automation is rolled out gradually depending on Meta approval; the first step is WhatsApp and Instagram DM.

Next step

If you haven't trained your assistant yet, start with the how to train the intusell AI article first — the foundation of this operation is built there. If you want to go deeper on the channel side, you can move on to the Instagram and WhatsApp automation article, and for automating service and quote appointments, the service appointment automation article. You can see the automotive solution page and the whole series on the all articles page. If you're curious about the same series in other sectors, the tour agency and clinic sections are good examples too.

To see live how it would work at your own dealership or service shop, request a demo or write directly to hello@intusell.com. In a 20-minute session, we open your inbox together and test the first response in the system.