Bank of Punjab — Voice AI for customer helpline automation.

The challenge

Bank of Punjab operates one of Pakistan's largest retail banking helplines, handling over 45,000 inbound calls per month across its branch network. The majority of callers — customers from Lahore, Rawalpindi, Faisalabad, and rural Punjab — speak Urdu or Punjabi as their primary language, yet the bank's existing IVR system required English input for account verification and menu navigation. Drop-off rates on routine self-service flows were high, and agents were spending the bulk of their working hours on calls that required no human judgement: balance checks, mini-statements, card status, and branch hours.

Before deployment, 78% of inbound calls required live agent handling even for fully routine queries. Average wait time during peak hours (10am–12pm and 4pm–6pm) exceeded four minutes, driving complaint volumes and eroding customer satisfaction scores. The bank needed a solution that could handle native Urdu and Punjabi speech accurately, integrate with their core banking system without a full infrastructure replacement, and be deployed entirely on-premise to satisfy SBP data-residency requirements.

The solution

Poocho AI deployed a voice AI layer on-premise within BOP's Lahore datacenter, sitting in front of the bank's existing telephony infrastructure and handling inbound customer calls in Urdu and Punjabi across five helpline use cases.

The five use cases configured at go-live: account balance enquiry, mini-statement delivery, card block and unblock, fraud dispute intake and case creation, and branch locator. The voice models were fine-tuned on banking-domain conversation data in Lahori Urdu and Punjabi, covering account product names, banking terminology, and the code-switching patterns common when BOP customers discuss transactions. Integration with BOP's core banking system was implemented via REST APIs, enabling real-time balance reads, transaction lookups, and card status updates. Customer identity is verified using CNIC-based authentication before any account data is returned. Escalations to human agents arrive with a pre-populated screen-pop — caller identity, conversation summary, and any case reference created during the AI interaction — so agents receive the call fully briefed.

Results

Measured over the first 90 days of live operation, the Poocho AI deployment reduced agent-handled volume for the five automated use cases from 78% to 15% of total inbound calls. First-call resolution on AI-handled interactions reached 89%. Average customer wait time dropped from over four minutes to under eight seconds. Customer satisfaction scores on AI-handled calls averaged 4.1 out of 5 on post-call IVR surveys — matching agent-handled call satisfaction scores for the same use cases.

"The Urdu and Punjabi recognition accuracy was the deciding factor — our customers speak the way they speak, and the system understood them from day one. We went from scoping to live calls in three weeks, entirely within our own infrastructure."

Deployment timeline