Kevin Dubois
Senior Principal Developer Advocate at IBM
Verbier, Switzerland
Actions
Kevin Dubois is often featured as a (keynote) speaker at conferences around the world, where he shares his passion and knowledge about developer experience, open source, cloud native development and Java. He is also an author, java Champion, and an accomplished software architect and platform engineer. Kevin currently works as a Senior Principal Developer Advocate at IBM, and is also Technical Lead for the CNCF Developer Experience Technical Advisory Group.
Multilingual and multicultural, Kevin speaks English, Dutch, French, and Italian fluently. Currently based in Switzerland, he has also lived in Belgium, Italy, Montana and Utah.
When he’s not coding or speaking at conferences, you’ll likely find Kevin exploring the great outdoors—whether he's hiking rugged trails, gravel biking through scenic routes, snowboarding down epic mountain slopes, or packrafting & kayaking on untamed waters.
Badges
Area of Expertise
Topics
Why Enterprise MCP Runs on Java
Most MCP examples are written in Python or TypeScript. Great for prototypes, but enterprises don't ship prototypes. They ship type-safe, robust, observable, secure services. Exactly what Java excels at.
And, perhaps contrary to popular belief, building MCP servers or clients with Java is not hard at all. It is as natural as creating REST servers and clients. Swap a few dependencies, annotate your methods, and your services speak MCP.
But MCP in Java isn't just about exposing data to LLMs. It can also vastly augment your AI development experience. We'll show how we built an MCP-based agent into the Quarkus framework that exposes live runtime intelligence to your code assistant: structured exceptions, dynamically discovered tools, extension-specific coding patterns, and version-aware documentation search. With this, your agent doesn't just write code; it can also get real-time feedback from the running application, recover from crashes, and learn patterns specific to the frameworks in your project.
Through real-world examples including IoT integrations and Kubernetes analysis agents, we'll show why Java is the natural home for enterprise MCP adoption.
From Laptop to Cluster: The Agentic AI Inner Loop on Kubernetes
Building agentic AI systems means juggling API keys for LLMs and MCP-connected tools, plus the burden of configuring those services correctly. Add expensive inference calls and highly customized dev setups, and the inner loop quickly becomes inner hell.
This session will demonstrate a streamlined inner-loop experience for agentic AI. We will develop, test, and iterate on multi-agent systems on our laptop, then deploy to Kubernetes with zero code changes. We'll show how to auto-provision local LLM inference, build agents with typed tool contracts, compose workflows, and test interactions with hot reload. We'll also show how MCP and/or A2A enable portable integration and separation of concerns, and how teams can switch to production-grade inference through configuration alone, with Kubernetes-native health checks, observability, and deployment patterns.
You'll leave understanding how to build and ship AI systems with open-source tooling and cloud native patterns you already know.
Beyond Prototypes: Building Enterprise-scale Agentic Systems
There has been a lot of progress in agentic frameworks (such as Langchain, CrewAI, Autogen, among others), most of them written in and targeting Python developers. These frameworks allow you to build multi-agent systems that are co-located inside the same application.
That works well for fast experimentation and building prototypes, but production systems live or die on scalability, security, observability and governance. At the end of the day agents are software that we need to ship, run an operate on production, much like any other type of enterprise software.
In this session we will show how to build distributed agentic, MCP-connected systems that are ready for enterprise scale. We'll cover real production patterns such as agentic orchestration patterns, MCP interoperability, agent/tool coordination, observability and tracing and enterprise integration reusing our existing platforms.
Agentic AI Patterns for Enterprise Software
Developing AI applications today isn’t just about experimental single-model interactions. Organizations are rapidly adopting AI and to do that, the requirements for enterprise software become increasingly more complex. Advanced Agentic AI systems address this need, where multiple specialized agents work together, each capable of independent reasoning.
The real challenge for architects lies in orchestrating these agents to collaborate effectively towards a common goal. Unfortunately though, "one-size-fits-all" or “off-the-shelf” approaches to coordination just don't work due to the complex nature of software.
In this session we'll explore the spectrum of agentic patterns, from reliable and predictable, but rigid workflows to highly flexible, autonomous agent orchestration using LLMs, and everything in between.
This talk will cover:
* The pros and cons of various agentic patterns.
* Practical demonstrations of how to combine these patterns in an enterprise software environment with Java, LangChain4j and its Quarkus extension.
* How to leverage the provided infrastructure for agent collaboration.
* The flexibility to implement and seamlessly integrate your own custom agentic patterns.
The Self-Healing Canary: Integrating Agentic AIOps into Your Releases
Standard progressive delivery is an essential safety net, but in most cases, a rollback is just the beginning of a long investigation. This session explores how to evolve from simple automated rollbacks to a self-healing release cycle by integrating an agentic AI system via the A2A protocol.
We will demonstrate an architecture where specialized agents analyze canary logs and metrics in parallel to provide high-fidelity health checks. If an issue is detected, the system immediately signals a rollback while simultaneously launching an asynchronous remediation workflow. This "coding agent" analyzes the specific error against the app's source code to either create a detailed issue description or propose a fix in the form of a pull/merge request.
To maintain performance and keep costs low, the system utilizes a hybrid model strategy. We run Small Language Models (SLMs) directly on a Kubernetes cluster for fast, local analysis and escalate to larger frontier models only when complex reasoning is required. Attendees will learn how to build this modular system and get access to the open-source implementation to start automating their own remediation loops.
KubeCon + CloudNativeCon Japan 2026 Sessionize Event Upcoming
RivieraDev Upcoming
KubeCon + CloudNativeCon India 2026 Sessionize Event Upcoming
DevBcn 2026 Sessionize Event Upcoming
Cloud Native Days Italy 2026 Sessionize Event
JCON EUROPE 2026 Sessionize Event
CNCF-hosted Co-located Events Europe 2026 Sessionize Event
Jfokus 2026 Sessionize Event
CNCF-hosted Co-located Events North America 2025 Sessionize Event
Maintainer Summit: KubeCon + CloudNativeCon North America 2025 Sessionize Event
BaselOne 2025 Sessionize Event
KCD Colombia Bogota 2025 Sessionize Event
WeAreDevelopers World Congress 2025 Sessionize Event
KubeCon + CloudNativeCon China
Progressive Delivery made easy with Argo Rollouts
DevTalks Romania
Create Your Own AI-Infused Java Apps with Ease
Red Hat Summit
Container + Boot = OS? Hold My Podman
Quarkus and LangChain4j: Build your first agentic AI-infused Java applications
Devoxx Greece
Easily create your own AI-infused Java apps with LangChain4j
KubeCon + CloudNativeCon Europe 2025 Sessionize Event
Devnexus 2025 Sessionize Event
Jfokus 2025 Sessionize Event
JChampions Conference 2025 Sessionize Event
Voxxed Days Ticino
Create Your Own AI-Infused Java Apps with LangChain4j
Voxxed Days Cern
Kubernetes. From 0 to Production with Java.
Tampa JUG + Tampa AI meetup
Welcome to the AI jungle, Now What?
Openshift Commons @ KubeCon US
Automate Security on OpenShift with a Trusted Application Pipeline
Santiago CNCF meetup: CNCF Cloud Native Sustainability Week
Is Serverless Powerfully Powerless?
JavaCro'24 Sessionize Event
digit
Welcome to the AI Jungle! Now What?
Infobip Shift 2024 Sessionize Event
JavaZone
Taming Kubernetes: Streamlining Inner-loop Development for Distributed Systems
WeAreDevelopers World Congress 2024 Sessionize Event
jPrime
Java, Life is Short
Great Indian Developer Summit
Taming Kubernetes: Streamlining Inner-loop Development for Distributed Systems
Devnexus 2024 Sessionize Event
KubeCon + CloudNativeCon Europe 2024
Is Serverless Powerfully Powerless?
KubeCon + CloudNativeCon Europe 2024
Tutorial: Progressive Delivery with Argo Rollouts
KubeCon + CloudNativeCon Europe 2024 Sessionize Event
Jfokus 2024 Sessionize Event
BeJUG
Funky Functions with Quarkus Funqy
KubeDay Singapore 2023 Sessionize Event
Open Source Summit Japan
Simplifying Containers and Kubernetes on Your Laptop with Podman Desktop
cdCon Japan
Tekton and ArgoCD, the Dynamic Duo for Secure Cloud Native CI/CD
JJUG CCC Fall 2023 Sessionize Event
J-Fall 2023 Sessionize Event
FooConf #2 Sessionize Event
DevFest Nantes
Workshop sur l'Intégration à l'ère du cloud avec Camel Quarkus
Devoxx Belgium
Kubernetes. From 0 to Production-Grade with Java
Infobip Shift 2023 Sessionize Event
Javazone
Quarkus Deep Dive
RivieraDev
A Story about Serverless Camels Living in Containers
Quarkus Deep Dive
Progressive Delivery in the Kubernetes Era
Voxxed Days Luxembourg
Next-Gen CI/CD with Progressive Delivery
JCON EUROPE 2023 Sessionize Event
KCD Italy
Tekton and ArgoCD: The Dynamic Duo for GitOps-based Continuous I/D/D
JNation 2023 Sessionize Event
KCD Colombia
Tekton and ArgoCD: The Dynamic Duo for GitOps-based Continuous I/D/D
Code Europe
Java, Life is Short!
Next-gen CI/CD with Gitops and Progressive Delivery
Code Europe
Java, Life is Short!
Next-gen CI/CD with Gitops and Progressive Delivery
Red Hat Tech Exchange
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top