Uncovering the Cloud Native Dust - We are back 2026'

After a long time, we’re back—refreshed and ready to showcase everything that’s changed. Join us in Ghent at Delaware HQ for an energizing technical session themed “Uncovering the Dust”, where we highlight the latest and greatest innovations, insights, and best practices.

Session 1: One cluster to serve them all: A central aks setup for multi-team delivery by Tibo Jacobs (Delaware)

Running a single central AKS cluster for multiple teams and applications sounds efficient, but without proper structure, it can quickly become a tangled mess. This session will show you how to set up a central AKS cluster that stays clean, secure, and easy to manage, even as teams and workloads grow.

Session 2: From scripts to agents: Orchestrating Cloud-Native operations with kagent by Massimo Crippa (Codit)

AI agents are quickly moving from experiments to first-class platform components. In this session, we’ll explore how kagent enables teams to build, run, and orchestrate AI agents the cloud-native way. We’ll dive into the supervisor pattern, showing how multiple specialist agents collaborate and how this approach aligns naturally with platform engineering principles.

Session 3: Learning Agent Behavior the Hard Way (DIY) by Philippe Bogaerts (Fortinet)

Agentic AI systems don’t just “chat” anymore. They take actions: they call tools, hit services, chain steps together, and sometimes do things that look … unexpected.

When that happens, we usually have lot's of opinions and some logs, but not enough ground truth.
What did the agent really call? What did it touch? What did it spawn or connect to? And which patterns keep showing up across runs?

In this talk I’ll share an ongoing hands-on experiment: a small Kubernetes sandbox where I run multiple agents and MCP servers built with different SDKs, then observe them using open source runtime security and telemetry. Think of it as putting agents under a microscope.
I'll combine Cilium for L4/L7 visibility, Tetragon for runtime process signals, and Elastic to store and correlate everything into a timeline you can actually reason about: flows, requests, processes, and “what happened next”.

Along the way, you also start to see the creative side of agents: how they “find a way” when they are blocked, how they compose tools in novel sequences, and how capabilities can effectively expand through combination and iteration, even when you didn’t design it explicitly.

This isn’t about claiming perfect detection. It’s about learning faster, spotting behavioral patterns, surfacing surprising toolchains, and exploring what practical governance might look like next: registries, gateways, and policy-controlled tool exposure.