Illimity modernizes commercial banking with Databricks and adopts LLMs for customer-centric chatbots

Overview

Illimity, an Italian digital bank, built its data architecture entirely around the Databricks Data + AI Platform to process data in real time, extract actionable insights and securely share it with partners. Databricks has supported Illimity's adoption of LLMs, using vector embedding and vector databases, to inform its knowledge base and power intelligent customer-centric chatbots. Illimity is also exploring Databricks Clean Rooms to monetize its architecture using deterministic or machine learning models without compromising confidentiality.

The challenge

Illimity's legacy architecture was built on disparate data warehouses, and Synapse lacked the flexibility the bank needed. With a huge amount of structured and unstructured data across disjointed sources, the bank wasn't able to operationalize its data at the rate and scale required, and needed a solution before launch.

The solution

Illimity built its data architecture entirely around the Databricks Data + AI Platform, using a lakehouse architecture with Databricks SQL for data warehousing and Unity Catalog for data lineage visibility. Databricks has supported Illimity's adoption of LLMs, using vector embedding and vector databases, to inform its knowledge base and power intelligent customer-centric chatbots. Illimity is also exploring Databricks Clean Rooms to monetize its architecture using deterministic or machine learning models without compromising confidentiality.

Reported business value

Databricks SQL performed queries faster than competitors like Synapse in a side-by-side comparison, and the managed solution let Illimity deliver everything in a short space of time ahead of launch, which the team cites as the most important factor given less than a year to get everything running.