Hannes Hapke

AI agents that autonomously select and invoke tools are becoming ubiquitous—yet their decision-making remains a black box. When an agent chooses to query a database instead of searching the web, what internal representations drive that choice?

Every conference showcases impressive agent demos. What they don’t show you are the 3 AM pages when agents go rogue, the customer support tickets when AI makes expensive mistakes, or the months of debugging why your “95% accurate” prototype becomes 60% reliable in production.

With the rise of deep learning applications, so do the questions of how to integrate larger machine learning models (e.g. transformer models) in Apache Beam data pipelines. At Digits, we took a deep dive into optimal integrations of our deep learning models to be consumed efficiently with Apache...

In this talk, Hannes is providing insights into using TensorFlow Extended (TFX) and Apache Beam for MLOps. He introduces how TFX is using Apache Beam for data pipeline tasks and for orchestration entire ML pipelines. The audience learned how to run ML production pipelines with Apache Beam, and...

Step-by-step walkthrough of how to write custom TFX components with Apache Beam to customize your ML pipelines beyond the standard components and tailor the components for their ML pipelines.