AUTOMOTIVE RETAIL

Service-reminder and feedback voice agents for an automotive dealer group

Service reminders and post-service feedback were handled by hand, with no CRM and weak follow-up. Wexa built two voice agents that run the full call cycle and escalate unhappy customers.

Download this case as PDF Book a demo

service-campaign call types
feedback dimensions rated on every call
tokens per call on a self-hostable open-weight model
rating triggers an automatic action-needed call

CLIENT: Multi-site automotive dealer group
REGION: India
WHEN: 2025
ENGAGEMENT: Proof of concept
WEXA COMPONENTS: Voice agents · schedulers · call evaluator · WhatsApp

01Case 31

The challenge

Manual reminder and feedback calling
No CRM: manual uploads from the dealer system
Negative feedback not followed up

What Wexa built

Service-reminder caller: campaign creation, daily scheduler, status-specific scripts, up to 3 attempts per customer
Feedback caller: six ratings, negative feedback routed to an action-needed call, closing call with the manufacturer's feedback link
Caller-evaluator agent scoring every call; dispositions written back
Token and telephony cost model for 2,000 calls a month

02Case 31

How it runs on Wexa

FigureHow this use case runs on Wexa: client systems connected, ontology discovered, context graph in the Wexa memory layer, agents and process flows, and governance. Highlighted components are central to this use case.

03Case 31

Solution workflow

FigureCustomer vehicle-service lifecycle covered by the agents.

04Case 31

Voice-agent architecture

05Case 31

Results

Measure	Before / without Wexa	With Wexa
Staff making reminder and feedback calls	8 callers	2 callers
Annual cost of the process	$48K	$12K
Service revenue from recovered visits per year	–	$120K
Time to implement the AI solution	3 months	2 weeks
AI build cost (one-time)	$96K	$7K
AI operating cost per year (models, infrastructure, upkeep, platform)	$65K	$29K
Total AI cost in year 1	$161K	$36K