Hi Dutch Databricks builders,
We are excited to announce our next in-person event, this time hosted by Xebia in their Amsterdam office.
The sessions are getting cooked and soon to be shared, book your space and set a placeholder in your agenda so that you dont miss this event.

Agenda:

17:30 - 18:25: Walk-in with drinks & food 🍺🍕
pizza (meet, fish, 2x vega);
IMPORTANT: gluten-free or vegan upon request
18:25 - 18:30: Introduction
18:30 - 19:15: Session I - Stop Trusting Markdown: Testing Agent Skills Across Harnesses with Omnigent
Abstract: Agent skills are increasingly shared as simple Markdown instruction bundles, but performance often varies across models and agent harnesses. This talk discusses Omnigent, Databricks’ open-source meta-harness, and explores how it can serve as a common experimentation layer across systems such as Claude Code, Codex, Cursor, and custom agents. By providing a unified way to run the same tasks, skills, tools, and evaluation workflows across different environments, Omnigent makes it practical to apply established agent and skill evaluation techniques at scale and compare results across harnesses. The broader argument is that skills should be treated as testable, versioned software artifacts with benchmarks and compatibility reports, rather than trusted solely because they worked in a demo.
Speaker: Max van den Hoven, Xebia
19:15 - 19:45: Break
19:45 - 20:30: Session II - Unity Gateway: Guardrails, Budgets & Governance for Your Whole Model Fleet Abstract: Enterprises don't run on a single model — teams reach for GPT for one use case, Claude for another, Llama or a fine-tuned open model for a third. Each new provider brings its own SDK, credentials, rate limits, and governance gaps. This session shows how Databricks' AI Gateway puts a single control plane in front of all of them. We'll walk through configuring guardrails, setting up automatic fallbacks so an outage at one provider silently routes to another, and enforcing rate limits and budgets across the whole fleet — plus the consolidated usage tracking and payload logging that give your governance and security teams a single audit trail. The takeaway: in the fast-changing world of AI, treat models as interchangeable, governed resources behind a common interface.
Speaker: Charlotte Blankenberg, Databricks Solution Architect.
20:30 - 21:00: Networking / drinks

Parking / Public Transport:
There is NO parking at location possible, it is advisible to travel by public transport if possible.

Don't miss this opportunity to connect, learn, and explore the incredible potential of Databricks features. Secure your spot now and be part of a community that’s shaping the future of data in the Netherlands.
Register today!