AI agents at the dealership, question by question
Short answers on calls, leads, aftersales, rollout and data security. You can ask Sufler about any of them in the chat.
The KPI Tech platform and Sufler
What does KPI Tech do?
KPI Tech builds an AI agent platform for car dealer groups. We join dealer data into a single graph, and on top of it we run tools that call, write, watch deadlines and close tasks. We cover sales, service, F&I, marketing and BDC.
What is Sufler in the KPI Tech platform?
Sufler is the consultant agent: an AI assistant for sales staff, service advisors and BDC. It knows the customer, the vehicle and the history, and during a conversation it queries the knowledge graph and suggests what to say. It works in text and in voice, in a management role and in an employee role.
More about the tool: SuflerDo management and staff see the same data in Sufler?
In Sufler, management sees data for the whole group and an employee sees only their own customers. Management asks about the group and gets an answer from the graph with a link to the actual records; an employee asks about their own portfolio. The role sets the scope, exactly as in the CRM.
How do you join customer data from the DMS, CRM and telephony into one record?
The knowledge graph joins the customer, their vehicles, work orders, visits, contacts and consents into one record. We pull data from the DMS, the showroom CRM, telephony, mailboxes, manufacturer feeds and marketing, and merge duplicates on phone, email and chassis number. Every other tool works on that layer.
Do the AI agents learn from what happens to their recommendations?
The Learning Loop checks what happened to scores and recommendations after they reached the CRM, and calibrates the parameters of the other tools on that basis. After a few months the recommendations are more accurate than at the start.
Phone, email and SMS
How do AI agents handle inbound and outbound calls at a dealership?
The Receptionist handles the phone: it answers inbound calls and calls the customers the Prospector points to. The recording and the note come back to the customer record, and decisions stay with the human.
Can an AI receptionist answer dealership calls after hours?
The Receptionist answers the phone during peak hours and after the dealership closes. It qualifies, books service and hands the call to a human when a decision is needed. Before it goes live it needs a few weeks of recordings from the Call Analyzer for calibration.
How does AI analyse recorded calls with dealership customers?
The Call Analyzer transcribes calls and scores them: customer intent and sentiment, adherence to the script, lost opportunities and complaint signals. The result lands on the customer record, next to their cars and visits. We process recordings under the monitoring regime of art. 22³ of the Polish Labour Code, with notice to the staff, and never assess employee emotions.
Does AI send emails and text messages to customers on its own or after human approval?
The Personalizer runs email and SMS communication, either automatically or with human approval, and writes conversation scripts. It builds the content from what is known about the customer and the car, so every customer gets a different message.
Leads and aftersales
How do you check leads from web forms and Meta before they reach a salesperson?
The Lead Validator checks leads from web forms and from Meta before they reach a salesperson: whether the contact is real, how hot the lead is, which model it concerns and when the customer plans to buy. The salesperson gets fewer empty enquiries.
How do you check the quality and timeliness of lead handling in the CRM?
The CRM Controller watches the quality and timeliness of work on leads: whether there is a note, a status and a next step, and how funnel conversion looks. It works on read-only access, so it changes nothing in the CRM.
How do you tell which customers have a reason to come back to the dealership?
The Prospector points out who has a reason to come back to the dealership. It comes in two variants: the service one looks at service intervals and warranty expiry, and the sales one at readiness to change the car and the end of a finance agreement. It hands the list to the Receptionist or to a person who makes the calls.
How can a dealership find service leads and dormant customers?
The Service Prospector points out service leads: dormant customers, recommended work left unbooked, service intervals, warranty expiry and service campaigns. Every reason is its own playbook, so you can see why a given customer is on the list.
How do you find customers ready for a conversation about a new car?
The Sales Prospector looks for reasons to talk about a new car: readiness to change the car, the move from service to sales, the end of a finance agreement and part-exchange potential. The end-of-term playbook only runs where we have confirmed access to finance data.
How can AI look after service quality and the dealership’s reputation after a visit?
The Quality Loop raises service quality and guards dealer reputation. It watches the post-visit SLA, catches dissatisfaction and complaints and makes sure they are put right. It invites customers to leave a review whatever they thought of the visit. We agree the scope with the importer’s quality programme.
Rollout, security and contract
How does an AI rollout at a dealer group work, and where does it start?
The rollout goes in stages, tool by tool, and at the end of each stage we check the number set in the acceptance criteria. It starts with a one-hour conversation about one dealership and one pipeline, after which you know which tool to implement first. We often start with Sufler or with the Call Analyzer, which shows what customer phone calls look like before we change anything.
How do you control an AI agent’s access to customer data, and what about GDPR?
Every agent has an identity, permissions and an action log, and the data of each group is isolated. An agent sees only what its role needs, and never more than its owner sees in the CRM and DMS. GDPR and the DPA are part of the contract. We send the architecture description on request: hi@kpitech.pl.
Does KPI Tech have a messenger for dealer groups designed for NIS2 requirements?
Sufler Connect is a secure messenger for a dealer group, designed for NIS2 requirements, in which AI agents work alongside employees. It has company-account sign-in, roles, multi-factor authentication, channels and alerts from the other tools.
What contract does a dealer group sign with KPI Tech, and does it include a right to exit?
We work under a master agreement for the group and a separate SOW for each tool and agent. The contract covers response times, the data processing agreement, a billing unit we do not change mid-term, and the right to exit with help migrating the data.

Have another question?
Sufler answers questions about the platform, the tools and the rollout in the chat. You can book a demo on the contact page.