Skip to content
Branemind
All case studies
Case studyFintech · Lending··6 min read

Collections on WhatsApp, run end-to-end by an agent

Recovery calls nobody answers, replaced by a conversation people actually finish. BM Relay negotiates, takes the payment, and knows exactly when to stop.

Contact rate
94%
vs 31% on voice dialer
Promise-to-pay kept
+38%
Cost per recovery
−62%

Measured against a baseline captured before the work started. One engagement, not a forecast for another business. See the methodology note below.

The outbound dialer was reaching under a third of the book, and the third it reached mostly resented it. Meanwhile the same customers were answering WhatsApp within minutes, just not to anybody at the lender.

The hard part was not the messaging

Sending a WhatsApp template is trivial. Running a collections conversation is not. The agent has to hold a negotiating position, recognise hardship, honour a settlement it offered four messages ago, take a payment mid-conversation, and recognise when to disengage entirely. That last one is the part that actually matters.

  • Hard stops on frequency, hours and language, enforced in the runtime rather than in the prompt.
  • A settlement ladder the agent can walk down but never past, with each rung a policy object, not a suggestion.
  • Instant handoff to a human on any distress signal, dispute, or legal keyword.
  • Every message, offer and payment written to BM CRM as it happens, so the ledger is never behind the conversation.
Contact rate
94%
First reply
2s
Promise-to-pay kept
+38%
Cost per recovery
−62%

The disengagement rules cost us recoveries in month one and won them back by month three. Customers who were not chased into a corner came back and settled. That is not a soft finding. It showed up in the roll rates.

We expected to recover more. We didn't expect complaints to fall by two thirds at the same time.
VP Collections

Methodology and privacy

  • Clients are described rather than named. Where a quote appears it is attributed to a role and published with approval.
  • Figures come from a single engagement and are not a forecast of what a different business would see. Volume, data quality and process maturity move them more than the technology does.
  • Baselines were captured before the work started. The measurement window and sample for any figure on this page are available on request.
  • Where a number is illustrative rather than measured, it is labelled as such in the text.
If this looks like your loop

Map your underwriting or collections loop

Ten questions on volume, controls and systems. Result first, email after.