Sebastian Diaz

Modern data platform migrations are no longer purely technical initiatives — they are business programs that reshape the foundation for operations, compliance, real-time decision making, and future AI adoption. In this session, Qubika shares how we partnered with FanDuel to migrate core workloads from Amazon Redshift to the Databricks lakehouse in a highly regulated, real-time environment. We cover the key engineering challenges, including rebuilding governance and metadata in Unity Catalog, validating data consistency at scale, and preserving developer velocity across large, multi-team migrations. We then show how these lessons led us to design an AI-powered Migration and Governance Agent — built natively on Databricks and powered by Lakebase as its persistent memory layer — to manage long-running workflows, reason over dependencies, and automate Databricks-ready governance artifacts. Attendees will leave with a practical blueprint to industrialize migrations and reduce risk.

Join us for this session on how to build AI finance agents with Databricks and LangChain. This session introduces a powerful approach to building AI agents by combining a modular framework that integrates LangChain, retrieval-augmented generation (RAG), and Databricks' unified data platform to build intelligent, adaptable finance agents. We’ll walk through the architecture and key components, including Databricks Unity Catalog, ML Flow, and Mosaic AI involved in building a system tailored for complex financial tasks like portfolio analysis, reporting automation, and real-time risk insights. We’ll also showcase a demo of one such agent in action - a Financial Analyst Agent. This agent emulates the expertise of a seasoned data analyst, delivering in-depth analysis in seconds - eliminating the need to wait hours or days for manual reports. The solution provides organizations with 24/7 access to advanced data analysis, enabling faster, smarter decision-making.