Maciej Szpakowski

Portfolio managers at Waterfall Asset Management evaluate hundreds of loans daily and track performance on Databricks. But loan “tapes” arrive as spreadsheets in high volume and inconsistent formats across originating institutions, making bids dependent on time-consuming data cleaning and harmonization before standard metrics and dashboards can be computed. Waterfall Asset Management and Prophecy built a specialized Claude Code “harmonization” agent that automates onboarding into a common schema, requiring only a final validation pass where users review AI confidence, reasoning, and lineage and make any edits. In production, WFAM achieved 93% first-pass accuracy — now approaching 100% — reducing reliance on data experts and materially accelerating investment decisions.

Legacy data stacks can't keep up with modern demands. We'll examine how SAP transformed Sales Performance Management by empowering analysts with Prophecy.ai, accelerating insights while preserving enterprise-grade governance. We'll also share practical examples of how AI Agents reduce engineering bottlenecks - onboarding new data sources, automating analysis, and speeding time to value.

Still coding data transformations by hand? Struggling with rigid, proprietary data prep tools? AI agents are flipping the script, reshaping data teams and delivering production-ready data preparation. Join this session to see how analysts, data scientists, and data engineers can build powerful, production-ready data pipelines simply by describing their intent in natural language. All in under 7 minutes. No complex UI or coding is required. Select datasets, join tables, apply filters, perform calculations - all just by chatting - and watch the pipeline materialize in real time, ready for deployment with documentation, testing, lineage, and versioning. Ready to leave slow, traditional data prep behind and be part of the next wave of innovation? You won’t want to miss this session.