Powering KPMG UK Audit's AI future with Databricks

Summary

KPMG UK is evolving its Audit data platform with Databricks to support AI-enabled analytics while preserving governance, rigour, and professional standards. The program converges structured data, advanced analytics, and AI on a unified cloud-native Lakehouse, with Databricks SQL replacing core SQL Server workloads and Delta underpinning the platform. Lakebridge assessed migration complexity, while Databricks-hosted large language models including Claude Sonnet and Genie Code helped convert T-SQL, refactor stored procedures, modularize queries, and suggest Delta-based optimizations under engineer review. This reduced refactoring time by around 60% and enabled modernization of more than 400 scripts and stored procedures in roughly three months. Databricks SQL Serverless provides elastic compute for spiky workloads, while Genie offers traceable, version-controlled SQL and Delta Sharing supports governed data exchange.

Context

KPMG UK’s Audit business handles complex, high-volume analytics across globally delivered audits, with seasonal peaks, diverse data volumes, and strict requirements for governance, lineage, transparency, and professional standards. The program aims to evolve an established data foundation for AI without compromising audit quality or control.

Approach / What changed

KPMG UK is consolidating Audit data, analytics, and AI on a cloud-native Lakehouse, migrating core SQL workloads from SQL Server to Databricks SQL. Lakebridge estimates migration complexity, while Claude Sonnet and Genie Code assist with SQL conversion and refactoring in a controlled, engineer-reviewed workflow. Serverless compute, Genie, Delta Sharing, data federation, and enablement initiatives extend the platform’s capabilities.

Takeaways

• AI-assisted migration reduced SQL refactoring time by around 60%, allowing more than 400 scripts and stored procedures to be modernized in roughly three months with engineer validation.
• Databricks SQL Serverless automatically scales managed compute for spiky Audit workloads ranging from thousands to billions of financial-data rows.
• Genie generates traceable, version-controlled SQL from natural-language questions, linking results to approved and auditable data sources.

Related reading