Tom Kaltofen
Striving to make data and algorithmic pipelines robust, reliable, and finally painless
Tom Kaltofen is the creator of mloda, an open‑source Python framework that separates transformation logic from data to enable reusable, consistent, and scalable feature engineering across Pandas, Spark, Polars, DuckDB, FastAPI, and more. Based in Berlin and maintaining the mloda project on GitHub and PyPI, he works at the intersection of data engineering and AI tooling.
Why AI Agents Fail on Enterprise Data and What Coding Agents Get Right
When AI agents fail on enterprise data, the root cause is usually the data layer, not the model. Coding agents avoid this because their context is deterministic by design. Enterprise data has none of that by default.
This talk introduces the handover layer pattern and demonstrates it live: an AI agent discovering transformations, applying PII redaction, and switching data sources without hardcoded paths.
Takeaways:
- How to separate data context failures from model failures
- A concrete architectural pattern for deterministic data access
- A live demo reproducible locally with open-source tooling