BANKING AND LENDING

Loan-protection cross-sell voice agent for a lender

Active-loan customers are the best audience for loan-protection cover, but outbound calling is expensive. Wexa built a voice agent that explains the plan, captures interest and sends the documents.

Download this case as PDF Book a demo

call outcomes logged automatically
document channels: WhatsApp and email
retry on unanswered calls

CLIENT: Consumer lender
REGION: India
WHEN: 2025–2026
ENGAGEMENT: Proof of concept
WEXA COMPONENTS: Outbound voice agent · WhatsApp and email · CRM update

01Case 32

The challenge

Manual outbound calling to eligible borrowers
Product explanation varies by agent
Follow-up documents sent late or not at all

What Wexa built

Eligible active-loan customers identified and called by the agent
Explains cover for job loss, medical emergency and accident, with monthly and yearly premiums
Sends brochures and policy documents by WhatsApp and email
Logs Interested / Follow-up / Not interested / Not connected, with automatic retries

02Case 32

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 32

Results

Measure	Before / without Wexa	With Wexa
Outbound calling agents	20 agents	4 agents
Annual cost of the process	$100K	$20K
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