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:

As a follow-up to my talk on generative AI for Java developers, I’ve developed a new presentation that focuses more on the Gemini large multimodal model by Google.

In this talk, we cover the multimodality capabilities of the model, as it’s able to ingest code, PDF, audio, video, and is able to reason about them. Another specificity of Gemini is its huge context window of up to 1 million tokens! This opens interesting perspectives, especially in multimodal scenarios.

Large Language Models, available through easy to use APIs, bring powerful machine learning tools in the hands of developers. Although Python is usually seen as the lingua franca of everything ML, with LLM APIs and LLM orchestration frameworks, complex tasks become easier to implement for enterprise developers.

Abstract

Large language models (LLMs) are a powerful new technology that can be used for a variety of tasks, including generating text, translating languages, and writing different kinds of creative content. However, LLMs can be difficult to use, especially for developers who are not proficient in Python, the lingua franca for AI. So what about us Java developers? How can we make use of Generative AI?

Read more...

At Devoxx France and Devoxx Greece, I had the pleasure to talk about my new social media journey on Mastodon. After a quick introduction about Mastodon and the Fediverse, I contrasted the key differences between Twitter and Mastodon. Then I shared some advice on how to get started, how to chose an instance, or clients you can pick from.

I moved on to important tips to get the best experience on the platform, and ensure to gather a great following:

• Workflows at a glance, benefits, key features, use cases
• UI interface in Google Cloud console
• Deep dive into the Workflows syntax
• Workflows connectors
• Demos
• Patterns and best practices

We went from a single monolith to a set of microservices that are small, lightweight, and easy to implement. Microservices enable reusability, make it easier to change and scale apps on demand but they also introduce new problems. How do microservices interact with each other toward a common goal? How do you figure out what went wrong when a business process composed of several microservices fails? Should there be a central orchestrator controlling all interactions between services or should each service work independently, in a loosely coupled way, and only interact through shared events? In this talk, we’ll explore the Choreography vs Orchestration question and see demos of some of the tools that can help. And we’ll explore some best practices and patterns to apply when adopting an orchestration approach.