I spoke at GDG Cloud Paris, hosted at Sfeir. The meetup featured four short presentations on cloud and AI technologies, and my talk focused on the Antigravity SDK for the Java Developer.

Most developers who have used Antigravity are familiar with its user-facing surfaces:

• Antigravity 2.0: the desktop agent manager
• Antigravity CLI: the terminal tool for command-line agent runs
• Antigravity IDE: the agent-centric code editor

Underneath these applications lies the Antigravity harness (actually, a Go binary!), which lets you programmatically define, host, and orchestrate AI agents with Gemini models. Google offers a Python SDK that wraps the Go binary. While the official SDK is currently available for Python, I built an unofficial Antigravity SDK for Java (with the help of Antigravity 2.0 itself) so JVM developers can build the same agent automations in Java.

In June, I had the please to come back to Devoxx Poland to give an overview of the various agentic coding tools offered by Google.

The big highlight was obviously Antigravity, but I started with Google AI Studio to show the various models in action, as well as how you can vibe code apps, and even deploy them in the cloud (on Google Cloud Run) or save them on GitHub.

In addition to those, I also uncovered Google Labs’ experiments, with Stitch to vibe design UIs for web apps and mobile apps, and Jules your proactive cloud-hosted agent working relentleslly on improving your GitHub projects.

At Devoxx France 2026 and JNation 2026, I had the pleasure of presenting a session on Agentic Design Patterns. In this talk, I explore how to move beyond basic LLM wrappers to build reliable, scalable, and sophisticated AI agent systems.

In the coming weeks, I’ll be blogging about some of these patterns, that I implemented using LangChain4j and ADK for Java.

Abstract

It’s time to dive into the deep end, far from “hello world” demos. To build your multi-agent systems, you often start by assembling classic bricks: sequential or parallel flows, or loops. The basics!

Read more...

At SnowCamp 2026, with my Cast Codeurs buddy Emmanuel Bernard of Hexactgon, I had the chance to deliver a talk on AI standards and protocols, with a big focus on MCP (Model Context Protocol), and A2A (Agent 2 Agent Protocol).

Without further ado, here’s the slide deck we presented:

This talk is based on the Devoxx 2025 deep dive session that I delivered with Emmanuel and my colleague Mete Atamel. As the talk wasn’t recorded during SnowCamp, I’ll share with you the 3h-long video from Devoxx below:

This week, I was on stage at the Tech Rocks Summit 2025 in the beautiful Théâtre de Paris. This is the first I’m attending this event, gathering a nice crowd of CTOs, tech leads, architects, and decision makers.

My talk focused on what everyone is talking about right now: AI Agents. And in particular, I was interested in sharing with the audience things I’ve seen work or not work in companies, startups, and via tons of discussions with AI practitioners I met at conferences, meetups, or customer meetings.

At Devoxx Belgium, I recently had the chance to present this new talk dedicated to ADK for Java, the open source Agent Development Kit framework developed by Google.

The presentation covered:

• an introduction to the notion of AI agents
• how to get started in a Java and Maven project
• how to create your first agent
• how to debug an agent via the Dev UI
• the coverage of the various tools (custom function tools, built-in tools like Google Search or code execution, an agent as tool, MCP tools)
• an overview of the different ways to combine agents into a multi-agent system: sub-agents, sequential agents, parallel agents, loop agents
• some details on the event loop and services (session and state management, artifacts, runner…)
• structured input / output schemas
• the various callbacks in the agent lifecycle
• the integration with LangChain4j (to give access to the plethora of LLMs supported by LangChain4j)
• the definition of agents via configuration in YAML
• the new long-term memory support
• the plugin system
• the new external code executors (via Docker containers or backed by Google Cloud Vertex AI)
• how to launch an agent with the Dev UI from JBang

Slides of the presentation

The slide deck of this session is embedded below:

I recently gave a talk titled “AI Agents, the New Frontier for LLMs”. The session explored how we can move beyond simple request-response interactions with Large Language Models to build more sophisticated and autonomous systems.

If you’re already familiar with LLMs and Retrieval Augmented Generation (RAG), the next logical step is to understand and build AI agents.

What makes a system “agentic”?

An agent is more than just a clever prompt. It’s a system that uses an LLM as its core reasoning engine to operate autonomously. The key characteristics that make a system “agentic” include:

Recently, I had the chance to deliver this talk on the mysteries of LLMs, at Devoxx France, with my good friend Didier Girard, It was fun to uncover the oddities of LLMs, and better understand where they thrive or fail, and why. I also delivered this talk alone at Devoxx Poland.

In this post, I’d like to share an update of the presentation deck, with a few additional slides here and there, to cover for example

Along my learning journey about generative AI, lots of questions popped up in my mind. I was very curious to learn how things worked under the hood in Large Language Models (at least having an intuition rather than knowing the maths in and out). Sometimes, I would wonder about how tokens are created, or how hyperparameters influence text generation.

Before the dotAI conference, I was invited to talk at the meetup organised by DataStax. I presented about all those things you never dared to ask about LLMs, sharing both the questions I came up with while learning about generative AI, and the answers I found and discovered along the way.

Retrieval Augmented Generation (RAG) is a pattern to let you prompt a large language model (LLM) about your own data, via in-context learning by providing extracts of documents found in a vector database (or potentially other sources too).

Implementing RAG isn’t very complicated, but the results you get are not necessarily up to your expectations. In the presentations below, I explore various advanced techniques to improve the quality of the responses returned by your RAG system: