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:

A very common question I get when presenting and talking about advanced RAG (Retrieval Augmented Generation) techniques, is how to best index and search rich documents like PDF (or web pages), that contain both text and rich elements, like pictures or diagrams.

Another very frequent question that people ask me is about RAG versus long context windows. Indeed, models with long context windows usually have a more global understanding of a document, and each excerpt in its overall context. But of course, you can’t feed all the documents of your users or customers in one single augmented prompt. Also, RAG has other advantages like offering a much lower latency, and is generally cheaper.

In the first article of this Advanced RAG series, I talked about an approach I called sentence window retrieval, where we calculate vector embeddings per sentence, but the chunk of text returned (and added in the context of the LLM) actually contains also surrounding sentences to add more context to that embedded sentence. This tends to give a better vector similarity than the whole surrounding context. It is one of the techniques I’m covering in my talk on advanced RAG techniques.

Recently on these pages, I’ve covered ADK (Agent Development Kit) for Java, launched at Google I/O 2025. I showed how to get started writing your first Java agent, and I shared a Github template that you can use to kick start your development.

But you also know that I’m a big fan of, and a contributor to the LangChain4j project, where I’ve worked on the Gemini support, embedding models, GCS document loaders, Imagen generation, etc.

Unlike Quarkus and Spring Boot, Micronaut doesn’t (yet?) provide a module to facilitate the implementation of MCP servers (Model Context Protocol). But being my favorite framework, I decided to see what it takes to build a quick implementation, by vibe coding it, with the help of Gemini!

In a recent article, I explored how to use the MCP reference implementation for Java to implement an MCP server, served as a servlet via Jetty, and to call that server from LangChain4j’s great MCP support. One approach with Micronaut may have been to somehow integrate the servlet I had built via Micronaut’s servlet support, but that didn’t really feel like a genuine and native way to implement a server, so I decided to do it from scratch.

MCP (Model Context Protocol) is making a buzz these days! MCP is a protocol invented last November by Anthropic, integrated in Claude Desktop and in more and more tools and frameworks, to expand LLMs capabilities by giving them access to various external tools and functions.

My colleague Philipp Schmid gave a great introduction to MCP recently, so if you want to learn more about MCP, this is the place for you.

In this article, I’d like to guide you through the implementation of an MCP server, and an MCP client, in Java. As I’m contributing to LangChain4j, I’ll be using LangChain4j’s mcp module for the client.

Retrieval Augmented Generation (RAG) is a great way to expand the knowledge of Large Language Models to let them know about your own data and documents. With RAG, LLMs can ground their answers on the information your provide, which reduces the chances of hallucinations.

Implementing RAG is fairly trivial with a framework like LangChain4j. However, the results may not be on-par with your quality expectations. Often, you’ll need to further tweak different aspects of the RAG pipeline, like the document preparation phase (in particular docs chunking), or the retrieval phase to find the best information in your vector database.

My colleague Jaana Dogan was pointing at the Anthropic’s MCP (Model Context Protocol) documentation pages which were describing how to build MCP servers and clients. The interesting twist was about preparing the documentation in order to have Claude assist you in building those MCP servers & clients, rather than clearly documenting how to do so.

MCP tutorials are great. There are no tutorials really.

"Copy these resources to Claude, and start asking some questions like..." pic.twitter.com/GG50DMWNLW

Read more...

This project demonstrates how to build a fully automated short story generator using Java, LangChain4j, Google Cloud’s Gemini and Imagen 3 models, and a serverless deployment on Cloud Run.

Every night at midnight UTC, a new story is created, complete with AI-generated illustrations, and published via Firebase Hosting. So if you want to read a new story every day, head over to:

→ short-ai-story.web.app ←

The code of this agent is available on Github. So don’t hesitate to check out the code:

First article of the year, so let me start by wishing you all, my dear readers, a very happy new year! And what is the subject of this new piece of content? For a while, I’ve been interested in analyzing trends and topics in social media streams. I recently joined Bluesky (you can follow me at @glaforge.dev), and contrarily to X, it’s possible to access its Firehose (the stream of all the messages sent by its users) pretty easily, and even for free. So let’s see what we can learn from the firehose!