By now, you’re certainly all familiar with the Model Context Protocol (MCP)? It’s the standard for connecting Large Language Models (LLMs) to tools and data. But if you look at the current ecosystem, you’ll see a lot of Python and TypeScript…

As a Java developer, you might be wondering: How can I easily and quickly run my own MCP servers?

On this blog, I’ve explained how to develop MCP servers with Quarkus and Micronaut. But thanks to a recent community contribution to LangChain4j, and the simplicity of JBang, building a local MCP server in Java is even easier and with zero boilerplate.

Today, let’s come back to one of my favorite generative AI topics: Retrieval Augmented Generation, or RAG for short.

In RAG, the quality of your generation (when an LLM crafts its answer based on search results) is only as good as your retrieval (the actually retrieved search results).

While vector search (semantic) and keyword search (BM25) each have their strengths, combining them often yields the best results. That’s what we often call Hybrid Search: combining two search techniques or the results of different searches with slight variations.

A month ago, I wrote about building a research assistant in Java, using the Gemini Interactions API, and the Deep Research agent. Today I wanted to revisit this project, but with the goal to make it more user-friendly, with a Javelit based frontend.

The Research Pipeline: From Query to Infographic

• First, the user enters the subject of the research.
• A button action triggers the research of possible topics about that subject (ie. the different possible facets or angles of the subject), using Gemini 3 Flash with Google Search activated.
• The user selects the facets they’re interested in, to restrict the research to only those aspects.
• Then the Deep Research agent kicks in, via the Gemini Interactions API, and spends a few minutes researching the topic.
• Once the final report is ready, Gemini 3 Pro creates a solid summary.
• The summary is used to generate a sketchnote with Nano Banana Pro.

A Look at the User Interface

Let’s say, as a user, I want to research information about the OpenClaw / MoltBot / ClawdBot personal AI assistant (unless it has again changed its name? 😃)

For my recent presentation at SnowCamp on AI Standards & Protocols for AI Agents, I decided to build an MCP server to access the arXiv research paper website where pre-print versions are published and shared with the community.

My goal was to shed light on some lesser-known aspects of the Model Context Protocol:

• 🛠️ While the majority of MCP servers use the tools feature to expose actions that LLMs can request to call,
• 📄 An MCP server can also share resources (and resource templates), exposing various static assets the AI app might be interested in,
• ✏️ And prompts (and prompt templates) that users can access and reuse to utilize the MCP server effectively.

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:

First of all, dear readers, let me wish you a happy new year! This is my first post on this blog for 2026. I’m looking forward to continuing sharing interesting content with you.

During my holiday break, I wanted to put my recent Java implementation of the Gemini Interactions API to the test. I implemented and released it with the help of Antigravity. My colleague Shubham Saboo and Gargi Gupta wrote a tutorial on how to build an AI research agent with Google Interactions API & Gemini 3. I thought this was a great opportunity to replicate this example in Java using my Interactions API Java SDK.

Google and DeepMind have announced the Interactions API, a new way to interact with Gemini models and agents.

Here are some useful links to learn more about this new API:

• An announcement is available on Google’s Keywords blog:
  Interactions API: A unified foundation for models and agents
• A more detailed article is available on Google’s developers blog:
  Building agents with the ADK and the new Interactions API
• The newly released Gemini Deep Research agent is now available via the Interactions API as well:
  Build with Gemini Deep Research
• The official documentation of the Interactions API.

About the Interactions API

The Rationale and Motivation

The Interactions API was introduced to address a shift in AI development, moving from simple, stateless text generation to more complex, multi-turn agentic workflows. It serves as a dedicated interface for systems that require memory, reasoning, and tool use. It provides a unified interface for both simple LLM calls and more complex agent calls.

In this article, I’ll guide you through the process of programmatically interacting with a web browser using the new Computer Use model in Gemini 2.5 Pro. We’ll accomplish this in Java ☕ leveraging Microsoft’s powerful Playwright Java SDK to handle the browser automation.

The New Computer Use Model

Unveiled in this announcement article and made available in public preview last month, via the Gemini API on Google AI Studio and Vertex AI, Gemini 2.5 Pro introduces a pretty powerful “Computer Use” feature.

Continuing my journey with Javelit, after creating a frontend for “Nano Banana” to generate images and a chat interface for a LangChain4j-based Gemini chat model, I decided to see how I could integrate an ADK agent with a Javelit frontend.

The Javelit interface for an ADK search agent

A Javelit interface for an ADK search agent

Yesterday, I uncovered the Javelit project in this article where I built a small frontend to create and edit images with Google’s Nano Banana image model.