Large Language Models (LLMs) are all becoming “multimodal”. They can process text, but also other “modalities” in input, like pictures, videos, or audio files. But models that output more than just text are less common…

Recently, I wrote about my experiments with Nano Banana 🍌 (in Java), a Gemini chat model flavor that can create and edit images. This is pretty handy in particular for interactive creative tasks, like for example a marketing assistant that would help you design a new product, by describing it, by futher tweaking its look, by exposing it in different settings for marketing ads, etc.

In previous articles, I explored how to create an MCP server with Micronaut by vibe-coding one, following the Model Context Protocol specification (which was a great way to better understand the underpinnings) and how to create an MCP server with Quarkus.

Micronaut lacked a dedicated module for creating MCP servers, but fortunately, recently Micronaut added official support for MCP, so I was eager to try it out!

Note: For the impatient, you can checkout the code we’ll be covering in this article on GitHub.

Read more...

Yesterday, we went bananas 🍌 creating and editing images with Nano Banana, in Java. Now, what about generating videos as well, still in Java, with Veo 3?

Especially since this week, Google announced that Veo 3 became generally available, with reduced pricing, a new 9:16 aspect ratio (nice for those vertical viral videos) and even with resolution up to 1080p!

In today’s article, we’ll see how to create videos, in Java, with the GenAI Java SDK. We’ll create videos either:

By now, you’ve all probably seen the incredible images generated by the Nano Banana model (also known as Gemini 2.5 Flash Image preview)? If you haven’t, I encourage you to play with it within Google AI Studio, and from the Gemini app. or have a look at the @NanoBanana X/Twitter account which shares some of its greatest creations.

As a Java developer, you may be wondering how you can integrate Nano Banana in your own LLM-powered apps. This is what this article is about! I’ll show you how you can use this model to:

Over the past few articles, we’ve taken a deep dive into the powerful agentic workflow orchestration capabilities of the Agent Development Kit (ADK) for Java. We’ve seen how to build robust, specialized AI agents by moving beyond single, monolithic agents. We’ve explored how to structure our agents for:

• Part 1: Flexibility with sub-agents — Letting an orchestrator LLM decide the best course of action.
• Part 2: Order with sequential agents — Enforcing a strict, predictable execution path.
• Part 3: Efficiency with parallel agents — Running independent tasks concurrently to save time.
• Part 4: Refinement with loop agents — Creating iterative processes for self-correction and complex problem-solving.

In this final post, let’s bring it all together. We’ll summarize each pattern, clarify when to use one over the other, and show how their true power is unlocked when you start combining them.

Welcome to the final installment of our series on mastering agentic workflows with the ADK for Java. We’ve covered a lot of ground:

• Part 1: Sub-agents for flexible, user-driven delegation.
• Part 2: Sequential agents for predictable, ordered processes.
• Part 3: Parallel agents for efficient, concurrent execution.

Now, we’ll explore a pattern that enables agents to mimic a fundamental human problem-solving technique: iteration. For tasks that require refinement, trial-and-error, and self-correction, the ADK provides a LoopAgent.

Let’s continue our exploration of ADK for Java (Agent Development Kit for building AI agents). In this series, we’ve explored two fundamental agentic workflows:

• First, we used LlmAgent with sub-agents to create a flexible, manager-and-specialists model.
• Then, we used the SequentialAgent to enforce a strict, linear order of operations.

But what if your problem isn’t about flexibility or a fixed sequence? What if it’s about efficiency? Some tasks don’t depend on each other and can be done at the same time. Why wait for one to finish before starting the next?

In the first part of this series, we explored the “divide and conquer” strategy using sub-agents to create a flexible, modular team of AI specialists. This is perfect for situations where the user is in the driver’s seat, directing the flow of conversation. But what about when the process itself needs to be in charge?

Some tasks are inherently linear. You have to do Step A before Step B, and Step B before Step C. Think about a CI/CD pipeline: you build, then you test, then you deploy. You can’t do it out of order… or if you do, be prepared for havoc!

Let me come back to the Agent Development Kit (ADK) for Java! We recently discussed the many ways to expand ADK agents with tools. But today, I want to explore the multi-agentic capabilities of ADK, by talking about sub-agent workflows.

In upcoming articles in this series, we’ll also talk about sequential, parallel, and loop flows.

The “divide and conquer” strategy

Think of building a complex application. You wouldn’t put all your logic in a single, monolithic class, would you? You’d break it down into smaller, specialized components. The sub-agent workflow applies this same “divide and conquer” principle to AI agents.

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.