Open Lakehouse + AI Meetup - Munich
Open Lakehouse + AI Meetup - Tuesday, November 3, 5:00 PM – 9:00 PM CET | Munich, DE
We're bringing together the open source and data engineering community for an evening focused on the latest in open lakehouse and AI architectures!
Whether you work on data infrastructure, contribute to open source, or want to dive into the future of AI and interoperable lakehouse systems, you’ll fit right in.
Don't miss this opportunity to accelerate your data journey and contribute to shaping the future of data and AI!
Agenda
5:00 - 6:00PM - Drinks & mingling
6:00 - Welcome remarks
🎙️ Viktor Kessler (Vakamo): Agentic Readiness Starts in the Catalog
🎙️ Helge Aufderheide (NVIDIA) : Accelerated Data Processing with NVIDIA
Networking / Break
🎙️ Robert Pack (Databricks): What is a Data Brick? Composing an agentic Lakehouse from Open Source projects.
🎙️ Nimar Blume (LangFuse): Making sense of large volume observability data: what is in your traces?
8:30 - 9:00 PM - Closing Remarks & Networking & bite
Livestream
Presentations and Abstracts
🌟Agentic Readiness Starts in the Catalog
AI agents get smarter by learning from each other: one agent writes a memory or drafts a skill, and the whole fleet reuses it. That reciprocity is also the risk. A single poisoned email can turn into a “helpful” skill that every agent follows the next day, with no record of who wrote it or who approved it. That’s why most agent projects stall at the CISO.
We will talk how to make agents CISO-ready with the same lakehouse machinery that already governs your data. Lakekeeper, the open-source Apache Iceberg REST catalog, gives every agent its own identity, OpenFGA grants and short-lived vended credentials scoped to its own datasets. Agents can propose skills but hold no key to publish them. A governance agent triages proposals with versioned rules it can’t change, a human approves, and every decision lands in an audit log and an Iceberg decision log.
Live demo included: three agents, one human, and a catalog that keeps saying no.
Viktor Kessler is Co-Founder of Vakamo and the creator of Lakekeeper, an Apache-licensed Iceberg REST Catalog. He’s a big believer in open standards like Apache Iceberg, which he sees as the backbone of today’s modern, composable Data & Analytics systems.
🌟Accelerated Data Processing with NVIDIA
When we hear the word "GPU", do you think Data Processing? In this talk you will learn why you should. You will see how accelerated Compute changes the economics and opens new possibilities to work with data in many of your standard tools, from pandas to databases.
Helge is a tinkerer at heart and passionate about innovation in traditional industries driven by new technologies. At NVIDIA, he focuses on the possibilities that open when bringing AI and big data to railway and factory environments.
🌟 What is a Data Brick?
Todays open source data + ai ecosystem features an astounding amount of production-grade projects, libraries, and services, many of which can interoperate or even more deeply integrated thanks to the ideas behind the Open Lakehouse and composable systems. In this talk we'll build a fully featured agentic lakehouse and examine the glue that keeps it all together.
Robert Pack is a Staff Developer Advocate at Databricks, where he works on the Open Lakehouse, and he’s a committer on Delta Lake. Before that he spent over a decade at BASF. Most recently he was Chief Technology Lead for its plant analytics platform. He studied process systems engineering at RWTH Aachen and Imperial College London.
🌟Making sense of large volume observability data: what is in your traces?
You've been ingesting traces for a long time and occasionally look at them. Maybe your agent analyzes a couple hundred over MCP. I will dive into how we summarize and cluster incoming traces at scale and present digestible patterns to our users.
Nimar Blume is a Senior Software Engineer at ClickHouse, where he works on Langfuse, the LLM observability platform. Before that, he co-founded and led tech at sento.io, a Munich startup automating B2B trade integrations. He studied engineering in Munich and computer science in Japan.