
Kumaran developed an automatic test case and script generation solution powered by a GenAI multi-agent architecture. Two key applications were delivered: a Test Case Generator and a Test Executor, producing test cases and scripts with 70–85% automation accuracy. The solution enabled automated validation of customer communication letters in PDF format using both generated and fixed test scripts, ensuring fine-grained validation that meets security and development standards.
A Tier-1 Global Bank partnered with Kumaran to automate test case and script generation for over 600 printed customer communication letters, achieving 70–85% automation accuracy and reducing manual effort by 70%. The engagement delivered a GenAI multi-agent solution — a Test Case Generator and Test Executor — that automated the full validation pipeline for customer communications in PDF format. For this bank, the challenge was not just volume — it was the precision required to validate formatting, text positioning, and layout against strict print specifications, at a scale that manual authoring simply could not sustain.
The bank produced hundreds of printed customer communication letters that had to strictly adhere to detailed print specifications. Every letter required test cases covering formatting, text positioning, images, and content accuracy — all written manually by the client's QA team. As communication volumes grew, the manual effort became unsustainable, creating bottlenecks in the release pipeline and increasing the risk of specification non-compliance. A scalable, automated approach to test generation and validation was essential.
Contact us today to learn more about our GenAI-powered test automation approach and the success story behind this engagement with the Tier-1 Global Bank.

ETL Migration Automation Accuracy
60–80%
A Tier-1 Global Bank was extensively reliant on Informatica for their ETL processes, resulting in high licensing, infrastructure, and operational costs. The client required a cost-effective, modern, cloud-based alternative and identified Azure Databricks as their preferred target platform for migrat

First-Response Time
Faster
Customer service representatives at a Tier-1 Global Bank were tasked with answering complex queries across a wide range of product procedures, rules, and features. The information needed to respond accurately was dispersed across the product website, internal SharePoint, documents, and training mate