AI on foojay.io - Friends of OpenJDK

How to Create a Spring Boot Fraud Scoring Service

Fri, 31 Jul 2026 08:45:43 +0000

Most Java teams who want a machine learning model in production end up standing up a Python service and calling it over HTTP. That works, but it buys you, as a Java developer, a second runtime, a second deployment pipeline, a network hop on every prediction, and a team boundary that turns retraining into someone else’s ticket.

Deep Netts removes that split: it’s a pure-Java deep learning library, so the model trains in Java, serializes to a file, and loads back into your Spring Boot application as an ordinary bean. Predictions become in-process method calls measured in microseconds, with nothing extra to deploy, secure, or monitor.

AI Found the Bugs. Who's Patching Your EOL Java Code?

Thu, 23 Jul 2026 15:26:53 +0000

Earlier this year an AI model found a flaw in OpenBSD’s TCP stack that had been sitting there for 27 years. The same scanning run turned up a 16-year-old bug in FFmpeg’s H.264 code.

How do you feel about AI being used to discover bugs in open source, across the board and at scale?

Because that’s what’s happening. It’s tough enough dealing with machine-speed vulnerability discovery in code that has active maintainers. What about all the code with no friendly pair of safe hands?

I Asked GitHub Copilot to Profile a Java App. It Found a Bug in My Heap Sizing, and Offered to Fix It

Tue, 14 Jul 2026 14:42:11 +0000

I built an extension to collapse the entire loop of running and measuring the performance of Java workloads, so it can be used within a place some developers are starting to consider their new “development environment” in the agentic AI era: the GitHub Copilot app .

The idea: Copilot-driven profiling

This extension is called JVM Pulse, and this is a walkthrough of one real run. JVM Pulse is a canvas extension for the GitHub Copilot app. It doesn’t hard-code how to build or run Java projects and it doesn’t need the user to be specific either. You click Run analysis, and Copilot does the project-specific work: it detects your build tool and JDK, writes or compiles a representative workload, and launches it with the right flags: unified GC logging and a JFR recording with settings=profile.

Building AI Systems with MongoDB: Implementing the Planning Pattern

Thu, 02 Jul 2026 10:00:00 +0000

Artificial Intelligence has swiftly evolved from a niche research topic to a technology that impacts nearly every aspect of the software industry. Developers now use AI to generate code, review pull requests, create documentation, and accelerate workflows through methods like vibe coding and specification-driven development. While these applications position AI as an engineering tool, a new trend is emerging: integrating AI directly into business workflows within applications.

This shift offers new challenges for software architects and engineers. Traditional applications rely on deterministic flows, where execution paths are explicitly defined by methods, conditions, loops, and business rules. In contrast, machine learning systems can make decisions during execution, select actions, and adjust dynamically based on context and available information. Architects must therefore design systems that balance the predictability of conventional software with the flexibility of AI-powered reasoning. The Planning Pattern is an effective approach for uniting these domains. Instead of having an LLM address a complex objective in a single step, this pattern breaks the goal into smaller, feasible tasks that interact with deterministic code, external services, and data sources. This creates a more reliable and observable path toward autonomous AI applications.

You’re invited to IntelliJ IDEA Conf 2026!

Mon, 29 Jun 2026 18:35:08 +0000

We are excited to invite you to IntelliJ IDEA Conf 2026, a free virtual event on September 8-9, 2026.

IntelliJ IDEA Conf is a celebration of the developer community, bringing together professionals who strive for excellence in software development. Join us for this free, live online conference and learn from industry leaders and experts on September 8-9, 2026.

You’ll be able to learn about a broad range of topics relevant to modern Java and Kotlin development, including language evolution, enterprise Java, Spring-based applications, build tooling, containerized workflows, JVM performance, and data access technologies. For more details, see the agenda below.

Building an AI-Powered Operations Assistant with Spring AI and MongoDB Atlas — Part 3: Stateful Workflows and Human-in-the-Loop

Mon, 29 Jun 2026 09:40:40 +0000

This is the third and final article in the series. Part 1 covered the RAG foundation — loading runbooks into a vector store and grounding model answers in real documentation. Part 2 added short-term and long-term conversational memory. This article introduces stateful workflow checkpointing, tool calls, and a pause/resume mechanism that lets multi-step investigations survive session boundaries.

The Remaining Gap

Where were we? At the end of Part 2 of our tutorial, we have an assistant capable of sustaining a conversation consisting of multiple exchanges and remembering the information exchanged across multiple sessions. For example, an operator can ask multiple questions regarding a CPU spike alert and will receive responses from the assistant that build upon one another, taking into account their preferences or past choices. In fact, across all sessions, the assistant will remember when the operator expressed a preference for using Helm charts for rollback operations and the fact that the payments service runs on a Kubernetes infrastructure consisting of 16 pods.

AI-Assisted Unused & Dead Code Removal

Sun, 28 Jun 2026 07:19:42 +0000

Why Your Codebase Is Forcing AI to Underperform, and What to Do About It

Your AI coding assistant is only as good as the codebase it works on. If your Java application carries years of dead & unused code, and most do, the AI spends its reasoning budget on code that nobody runs. The result is more hallucinations, worse suggestions, and higher token costs. Here’s what to do about it.

Systematic AI Coding: My Takeaways from the Eclipse Foundation Workshop in Brussels

Tue, 23 Jun 2026 19:48:42 +0000

Most developers using AI tools are still guessing. The Eclipse Foundation’s first AI Coding Workshop in Brussels was built to change that. It’s a brand new format they launched in Brussels, which makes sense: most of the Eclipse event team is based there. They plan to bring it to more cities from here, so keep an eye out if you want to attend such a workshop in the future. They offered 10 free tickets to share with the BeJUG and Foojay community. And in all honesty, I used one for myself. Jonas Helming from EclipseSource led the workshop, with a fun quiz hosted by Thomas Froment in the afternoon. Here’s what I took away.

Foojay Podcast #99: Testing the Untestable: LLM Security for Java Developers with Tiberius

Mon, 22 Jun 2026 06:54:00 +0000

Your AI-powered Java application is live in production. But have you actually tested whether it can be jailbroken or manipulated into leaking data it should never reveal? In this episode, Iryna Dohndorf walks us through Tiberius, an open-source security testing library for LLM applications in Java, and explains why everything you know about unit testing needs a rethink when non-determinism is part of the design.

YouTube

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

Building an AI-Powered Operations Assistant with Spring AI and MongoDB Atlas — Part 2: Conversational Memory

Wed, 10 Jun 2026 19:23:46 +0000

This is the second article in a three-part series. Part 1 covered the RAG foundation — loading runbooks into a vector store and wiring them to a language model. Part 3 will introduce stateful workflow checkpointing with pause and resume.

The Problem with Stateless Chat

In the first part of the series, we successfully created a chat interface where an operator can ask questions and receive answers based on the actual content of the runbooks they have uploaded and embedded in the system. For example, they can ask in the chat, “What should I check when my server’s CPU usage exceeds 80%?” and the assistant retrieves the relevant sections from the various runbooks and assembles a coherent and concrete response.

Why Spring Teams Don't Need a Second Runtime for AI Agents

Wed, 10 Jun 2026 19:02:58 +0000

A JVM-native runtime for building, governing and operating AI agents on existing Spring infrastructure.

Every time a Spring team decides to add AI agents to a production system, the story tends to follow the same arc. A few prototypes are built, several frameworks are evaluated, and then a new reality emerges: the project is no longer just about adding agents. It is about operating a new platform.

With that new runtime come new deployment pipelines, new monitoring mechanisms, additional security reviews, and new operational responsibilities.

"Agentic" Was Everywhere at Money20/20 Amsterdam

Fri, 05 Jun 2026 08:55:48 +0000

I walked the floor at Money20/20 in Amsterdam with a simple little mission: count the first ten vendor booths using “AI,” “agent,” or “agentic” in their pitch.

My first impression was that this would be hard. Hundreds of organizations, and the buzzwords felt oddly absent — payments, core banking, compliance, the usual fintech furniture, but not the wall-to-wall “agentic everything” I’d braced for. I jotted down my first ten and thought: huh, AI is barely here.

Tiberius: A Security Testing Framework for LLM Applications in Java

Thu, 04 Jun 2026 20:09:09 +0000

How do you write a regression test for a system that is non-deterministic by design?

The Problem {#h2-0-1-the-problem}

Large Language Models have moved from research artifacts to production infrastructure. Java applications are embedding them into customer-facing services via Spring Boot, and e.g. LangChain4J — for document summarization, customer support, healthcare assistance, and financial guidance, to name just a few. The deployment surface is growing faster than the security tooling.

The vulnerability landscape is empirically well-established. Horlacher, Vifian, and Zagidullina (2026) [4] red-teamed gpt-oss-20b and found that adversarial techniques achieved alarmingly high Attack Success Rates, while non-adversarial probing exposed pervasive stereotypical defaults — both consistent across English and Swiss German. Their conclusion: “current alignment mechanisms have not fully resolved jailbreaks and inherent bias, posing critical challenges for automated decision-making.”

BoxLang AI 3.2.0 — Image Generation, Web Search, Fluent Audio, Agent Registry & MCP Observability

Tue, 02 Jun 2026 12:27:07 +0000

BoxLang AI 3.2.0 is here, and it’s a landmark release. We’re shipping five major features: image generation, web search, a fluent audio builder API, a centralized agent registry, and deep MCP observability along with a suite of analytics improvements and a critical bug fix. Let’s dig in. 🎉

🖼️ Image Generation — aiImage()

You can now generate images directly from BoxLang using any provider that supports text-to-image generation. The aiImage() BIF follows the same fluent, chainable philosophy as the rest of bx-ai then act on the result with expressive method calls.

Jakarta EE is Ready for AI – Five Talks from OCX26 That Prove It

Tue, 02 Jun 2026 11:41:01 +0000

Back in April I had the pleasure of attending Open Community Experience 2026 in Brussels - the Eclipse Foundation’s flagship open source conference. It’s always good to be in a room (or a few rooms 😉 ) with people who really care about the technology they work with. Several of my colleagues and friends were speaking - watching them present work they’ve spent serious time on is one of the better parts of this community.

Foojay Podcast #97: From Scripting Language to AI Powerhouse: How BoxLang Is Redefining JVM Development

Mon, 01 Jun 2026 06:57:25 +0000

BoxLang is a modern dynamic JVM language built for rapid application development. It’s 100% Java-interoperable, compiles to JVM bytecode, and deployable anywhere from OS to AWS Lambda to Spring Boot. In this episode, we sit down with Luis Majano (CEO of Ortus Solutions and creator of BoxLang) and Cristobal Escobar (BoxLang community manager) to dig into the wave of innovation that has hit the platform over the past few months.

Free Webinar: Making AI useful for Java developers in Real Applications with BoxLang!

Fri, 29 May 2026 15:43:47 +0000

AI is everywhere right now, but for many development teams, the biggest question is no longer “What is AI?” it’s “How do we actually use it in real applications in a secure, practical, and maintainable way?”

That’s exactly what we’ll explore in our upcoming free June webinar:

Making AI Useful in Real Applications

A Practical Guide to Secure and Effective AI Development

Join Bill Reese, Senior Developer at Ortus Solutions , for a practical session focused on bringing AI into real-world applications using BoxLang and modern JVM development patterns.

Enterprise Java quality gates in the age of AI

Fri, 29 May 2026 07:00:00 +0000

People and AI can write code together, but enterprise repositories still need deterministic quality gates to protect code quality.

Enterprise quality is a scaling problem

Enterprise Java development is not only about writing correct code. It is about keeping a large, long-lived codebase understandable, reviewable and safe to change while many people and many tools touch it over time.

Context Is a Budget — Reducing Token Usage in AI-Assisted Development

Fri, 22 May 2026 12:52:06 +0000

Eight levers and three workflow patterns that pay for themselves in a week.

A team of fifty developers can quietly burn $30,000 a month on AI coding assistants without anyone noticing. Premium-request quotas vanish by the third week. The bill arrives. Nobody has a story for where it went.

The cost is the obvious pain. The other two are sneakier:

Latency. Bigger contexts take longer. The model thinks more, but you also wait more.
Context rot. This is the surprising one. Anthropic and Chroma have both shown that as the context window fills up, model recall and reasoning degrade — even well inside the advertised window. The 200K-token model is genuinely worse at the 150K mark than at the 20K mark. More context is not free; past a point, it’s actively harmful.

The mental model that fixes all three: stop treating context as a free buffet. Treat it as a budget you spend on every turn.

Introducing skills.boxlang.io — The Open Agent Skills Ecosystem for BoxLang & the Ortus World

Thu, 21 May 2026 11:42:26 +0000

Today we’re launching something we’ve been quietly building for months: skills.boxlang.io — a public, agent-agnostic directory for AI skills covering BoxLang, ColdBox, TestBox, CommandBox, and the entire Ortus ecosystem.

If you’ve ever pasted a 400-line system prompt into yet another AI agent, watched two of your bots drift onto subtly different versions of the same coding standard, or spent half a Friday afternoon trying to convince an LLM that BoxLang is not Java and is not CFML, or how to code for Modern CFML; this launch is for you. 🎯

From Zero (Really Zero) to OpenTelemetry

Tue, 19 May 2026 13:36:11 +0000

Here’s a super awesome prompt (e.g., for Claude Code) that you can use with https://github.com/dash0hq/agent-skills , the free collection of skills for AI coding agents to make applications observable with OpenTelemetry, such as with Dash0 .

And the end result is this, a view into the traces of your application (without anything at all at the start of the process).

The Super Awesome Prompt

Take a careful look below: before doing this prompt, not only do we not have an application that is instrumented with OpenTelemetry yet. Not only do we not have the agent we need to do the instrumentation yet.

AI-Powered Code Review Assistant: Automated Code Analysis with Spring AI and MongoDB

Thu, 14 May 2026 17:09:39 +0000

Code reviews catch bugs before they ship, but they take time. Most teams rely on manual review or basic linters that flag syntax issues but miss deeper problems like subtle resource leaks, poor exception handling, or security anti-patterns. Static analysis tools help, but they work with rigid rules that cannot generalize across code variations. A rule that catches catch (Exception e) {} will miss catch (Throwable t) { return null; }, even though both are the same underlying problem.

BoxLang AI Series: Complete Guide to Building AI Agents

Thu, 14 May 2026 09:26:48 +0000

The world of AI development is moving fast, but building real, production-ready AI agents doesn’t have to be complex.

This series walks you step by step through how to design, build, and deploy AI agents using BoxLang AI. Whether you’re exploring AI for the first time or looking to modernize your current applications, these guides will help you move from concept to implementation with clarity.

Start Here: A Practical Overview

If you’re new to BoxLang AI or want to understand what’s possible before diving into the technical details, start here:

How to Develop AI Agents Using BoxLang AI: A Practical Guide

Tue, 12 May 2026 12:52:39 +0000

AI agents are transforming how we build software. Unlike traditional chatbots that just answer questions, agents can reason about what tools they need, decide when to use them, chain multiple actions together, and remember what happened earlier in a conversation.

In this tutorial, I’ll show you how to build a real-world AI agent using BoxLang AI — the official AI framework for the BoxLang JVM language. We’ll build SupportBot, an e-commerce customer support agent that can look up orders, check inventory, issue refunds, and answer questions grounded in your knowledge base.

Explore Spring AI SDK – Amazon Bedrock AgentCore – Part 3

Sun, 10 May 2026 09:09:00 +0000

In Part 1 and Part 2 , we explored the Spring AI SDK and Amazon Bedrock AgentCore features, including the agentcore runtime starter and integration of agentcore memory. In this article, we will explore the integration of AgentCore built-in tools, including the Browser and Code Interpreter features.

Repository containing the companion code for the tutorial. Go to GitHub {#https://github.com/bsmahi/simple-spring-boot-agent}. Built-In Tool Browser

The use case I am trying to build here is for the given URL; it navigates the entire website and retrieves the content and gives key points and the summary of the page using the AgentCore Browser tool.

BoxLang AI Deep Dive — Part 7 of 7: MCP — The Protocol That Connects Everything

Thu, 07 May 2026 21:51:08 +0000

BoxLang AI 3.0 Series · Part 7 of 7

The AI ecosystem has a tool problem. Every framework has its own way of defining tools, every agent has its own way of calling them, and every integration requires custom code on both sides. An agent built in Python can’t easily use tools built in Java. An MCP server written for Claude Desktop can’t easily be consumed by a BoxLang agent without a custom adapter.

Building an AI-Powered Operations Assistant with Spring AI and MongoDB Atlas — Part 1: RAG Foundation

Thu, 07 May 2026 19:22:11 +0000

This is the first article in a three-part series. Part 2 covers short-term and long-term memory; Part 3 introduces stateful workflow checkpointing with pause/resume.

The problem

It’s 2 a.m. Suddenly, an alert pops up indicating abnormal CPU usage on the payment services. The on-call engineer opens their laptop, logs into the monitoring dashboards, and begins the hunt. One by one, he searches the runbooks on Confluence, checks the Slack chats, and opens the GitHub wikis and documents shared during the design phase. By the time he finds any useful information, ten minutes have already passed.

BoxLang AI Deep Dive — Part 6 of 7: Memory Systems & RAG — Building AI That Remembers

Tue, 05 May 2026 15:10:15 +0000

BoxLang AI 3.0 Series · Part 6 of 7

A chatbot with no memory isn’t a conversation — it’s a series of isolated queries. Every message starts from scratch. The user has to re-explain who they are, what they’re working on, and what was just said. It’s exhausting, and it signals that the AI isn’t really listening.

Memory is what separates a useful AI application from a toy. BoxLang AI ships with one of the most comprehensive memory systems in any AI framework — 20+ memory types across two major categories, vector embedding support for semantic retrieval, 30+ document loaders for RAG pipelines, and a per-call identity routing system that makes multi-tenant applications safe by default.

BoxLang AI Deep Dive — Part 5 of 7: One API, 17 Providers — The Provider Architecture Deep Dive

Wed, 29 Apr 2026 16:38:08 +0000

BoxLang AI 3.0 Series · Part 5 of 7

Vendor lock-in is the silent killer of AI projects. You pick OpenAI, build everything against the OpenAI API, and then GPT-5 launches at three times the price. Or a competitor launches a model that’s faster for your use case. Or you need to self-host for compliance. Or your client is on AWS and wants Bedrock.

Every time the answer to “can we switch providers?” is “it would take months,” something went wrong architecturally.

Explore Spring AI SDK – Amazon Bedrock AgentCore – Part 2

Mon, 27 Apr 2026 09:09:00 +0000

If you’re joining us from Part 1 or need a quick refresher on the architecture, listen to this brief overview of how Spring AI and Amazon Bedrock work together. Generated using Notebook LLM for my previous article {#https://foojay.io/today/spring-ai-amazon-bedrock-sdk-guide/}

In this article, we explore one of the AgentCore capabilities i.e., memory Source: Amazon

To begin, enable AgentCore memory for the agent you built earlier.

Step 1: Add the Ai model and AgentCore memory dependencies

<dependency>
 <groupId>org.springframework.ai</groupId>
 <artifactId>spring-ai-model</artifactId>
</dependency>
<dependency>
 <groupId>org.springaicommunity</groupId>
 <artifactId>spring-ai-agentcore-memory</artifactId>
</dependency>

Step 2: Create Short/Long Term in AWS Management Console

Navigate to Amazon Bedrock AgentCore > Memory to create short/long-term memories. AgentCore Memory

Building a Personalized Content Delivery System

Thu, 23 Apr 2026 15:10:45 +0000

Recommendation engines have a reputation for requiring specialized ML infrastructure: matrix factorization pipelines, training jobs, and model serving layers. That is one way to do it, but not the only way. If your data already lives in MongoDB and your application runs on Spring Boot, you can build a practical recommendation system using tools you already have. MongoDB aggregation pipelines handle the scoring math server-side, and Atlas Vector Search adds semantic matching without a separate vector database.

BoxLang AI Deep Dive — Part 4 of 7: Middleware — The Missing Layer in Every AI Framework 🧵

Thu, 23 Apr 2026 14:25:53 +0000

BoxLang AI 3.0 Series · Part 4 of 7

Here’s the question every team eventually asks about their AI agents: how do we test these things?

Agents make live LLM calls. They invoke real tools. They have non-deterministic outputs. Standard unit testing approaches fall apart. You can’t mock every provider. You can’t replay a conversation from three weeks ago. You can’t confidently tell stakeholders that the agent you deployed today behaves the same way it did when you signed off on it.

BoxLang AI Deep Dive — Part 3 of 7: Multi-Agent Orchestration — Building AI Teams That Work 🌲

Tue, 21 Apr 2026 08:32:06 +0000

BoxLang AI 3.0 Series · Part 3 of 7

A single agent is useful. An orchestra of agents is powerful.

The problem with most multi-agent frameworks is that the orchestration layer is bolted on — you’re managing agent references manually, passing outputs between them by hand, and hoping you haven’t introduced a cycle. There’s no concept of hierarchy. No cycle detection. No way to ask “who’s in charge here?” or “how deep in the tree am I?”

Explore Spring AI SDK - Amazon Bedrock AgentCore - Part 1

Mon, 20 Apr 2026 13:44:54 +0000

Introduction

Artificial intelligence has rapidly expanded across every industry since the inception of ChatGPT. It represents a breakthrough in how we build and use software. Moreover, this breakthrough technology has driven major transformation. At the same time, it has created significant noise and hype.

Today, AI is no longer experimental. Instead, it has become essential, much like electricity and the internet. As a result, it now plays a key role in our daily lives. Overall, this shift reflects strong technological acceleration across industries.

BoxLang AI Deep Dive — Part 2 of 7: Building a Production-Grade AI Tool Ecosystem

Thu, 16 Apr 2026 09:27:15 +0000

BoxLang AI 3.0 Series · Part 2 of 7

Function calling is where most AI frameworks look deceptively simple on the surface and turn into a mess underneath. You define a tool, pass it to the LLM, and when the LLM calls it — who handles the lifecycle? Who fires observability events? Who serializes the result? Who resolves the tool by name when the only thing you have is a string?

BoxLang AI Deep Dive — Part 1 of 7: The Skills Revolution 🎓

Tue, 14 Apr 2026 11:50:53 +0000

This article is part of our 7-part deep dive on building production-ready AI systems with BoxLang.

BoxLang AI 3.0 Series · Part 1 of 7

Every AI framework eventually hits the same wall: your system prompts start drifting. Agent A has a slightly different version of the SQL rules than Agent B. The tone policy on your support bot is three weeks behind the tone policy on your documentation bot. Someone copy-pasted the wrong version. Nobody noticed.

BoxLang AI v3 Has Landed - Multi-Agent Orchestration, Tooling, Skills and so much more

Mon, 06 Apr 2026 12:03:58 +0000

It’s been a while since we’ve shipped something this big. BoxLang AI 3.0 is a ground-up rethink of how AI agents, models, and tools work in the BoxLang ecosystem — and it lands with ten major features at once.

The headline is the AI Skills system : a first-class implementation of Anthropic’s Agent Skills open standard that lets you define reusable knowledge blocks: coding styles, domain rules, tone policies, API guidelines once in a SKILL.md file and inject them into any number of agents and models at runtime. No more copy-pasting the same system-prompt boilerplate everywhere. Skills are versioned, composable, and come in two modes: always-on (full content in every call) and lazy (only a name + description until the LLM asks for more).

Best practices for Mastering AI Agents, Subagents, Skills & MCP

Mon, 30 Mar 2026 18:55:59 +0000

A practical guide to the five best practices every developer should apply when working with AI agents, subagents, skills and MCP servers — from choosing the right model and writing precise prompts, to defining agent behaviour with SDD, isolating context with Claude Code subagents, securing MCP calls, and guiding agent response quality with guardrails.

§0 📖 Where This Fits in the Series

This article assumes you already know what MCP is and have used or built at least one Agent.

Does Language Still Matter in the Age of AI? Yes — But the Tradeoff Has Changed

Wed, 25 Mar 2026 16:37:20 +0000

I keep hearing the same question in architecture reviews, slack threads, and conference Hallways:

“If AI is writing the code, does language even matter anymore?”

It does. More than ever, actually — just not for the reasons we’ve been arguing about for the last decade.

The Bottleneck Has Moved

For decades, we optimized for developer productivity. How fast can someone write code? How expressive is the language? How quickly can we ship features?

How We Built a Java AI Agent by Connecting the Dots the Ecosystem Already Had

Wed, 25 Mar 2026 09:00:00 +0000

Everyone assumes you need Python to build AI agents. But the Java ecosystem already has every piece: Spring AI for LLM integration, Spring Events for decoupled messaging, JobRunr for reliable background jobs, and Spring Modulith for clean architecture. We didn’t build anything new. We connected the pieces that were already there.

The result is ClawRunr (everyone calls it JavaClaw, and we’ve stopped correcting them). An open-source AI agent runtime, written in pure Java. You can chat with it on Telegram or in the browser, ask it to summarize your emails every morning, schedule reminders, browse websites, run shell commands, connect external tools via MCP, and teach it new skills at runtime by dropping a Markdown file into a folder.

JC-AI Newsletter #15

Fri, 20 Mar 2026 07:56:01 +0000

Over the past two weeks, the field of artificial intelligence has continued its remarkable pace of advancement. As AI becomes increasingly woven into the fabric of daily life, shaping how we work, communicate, and make decisions, it is both timely and valuable to step back and understand the broader trajectory of this technology. Whether the developments around us feel promising or challenging, one truth remains clear: AI is not simply leaving. It is here to stay, and understanding its evolution is essential from many perspectives.

BoxLang 1.11.0 Release

Tue, 17 Mar 2026 09:40:04 +0000

We’re proud to announce BoxLang 1.11.0, a highly focused performance and stability release that delivers measurable speed improvements across every BoxLang application, with zero code changes required. The team invested deeply in bytecode generation, class loading, lock management, and type casting to produce one of the most impactful runtime optimization releases to date. Alongside the performance wave, this release resolves critical concurrency bugs, hardens DateTime handling, and ships powerful new developer tooling.

No Keys, No LLM: Building a Wikidata Definition API with Embabel

Thu, 05 Mar 2026 08:00:25 +0000

TL;DR

I built a Spring Boot 4 API that defines terms via Wikidata.
The app is fully reproducible: no API keys and no model installation needed.
Embabel orchestrates the pipeline as a sequence of actions to achieve the goal DefinitionResult.
The logs show planning, execution, and typed object binding—the most useful part for teaching agentic flows.

I wanted a demo that is simple , reproducible , and still shows agentic orchestration in a way that’s easy to explain on video.

JC-AI Newsletter #14

Tue, 03 Mar 2026 15:11:53 +0000

Two weeks have passed and a lot have been happening on the field of artificial-intelligence.

Two weeks have passed and a lot has been silently yet visibly happening in the field of artificial intelligence. This newsletter brings interesting developments, including Dario Amodei’s (Anthropic) view on the progress achieved in the LLM field and his response to the utilization of these models for specific kinds of military purposes, as well as OpenAI’s response to it. Aside from the fact that development may follow more sigmoids instead of exponential progress, it is important to have awareness of utilization across branches. Does prompting and clarifying the goal influence agent responses, and if so, how? How far are we from reliable robotics applications? How much bias is introduced when clinical data is being analyzed?

Shaping Jakarta Agentic AI Together

Mon, 02 Mar 2026 11:15:46 +0000

Last week, Eclipse Foundation and Payara hosted Jakarta Agentic AI, An Open Conversation, an open house Jakarta TechTalk session, exploring a brand new initiative under the Eclipse Foundation. If you could not join us live, the full recording is now available.

What is Jakarta Agentic AI?

Jakarta Agentic AI is an exploratory project looking at how AI agents could be built, deployed and run within Jakarta EE runtimes. As AI systems increasingly move from simple inference to autonomous, agent-based behaviour, the question becomes how these systems fit into enterprise Java environments that value reliability, security, and portability.

Translating a Website into 8 Languages with AI Agents in One Night

Thu, 26 Feb 2026 14:15:15 +0000

How I used Claude Sonnet 4.6 and fleets of GitHub Copilot Coding Agents to internationalize java.evolved — from spec to deployment

java.evolved is a static site I built to showcase modern Java patterns side-by-side with their legacy equivalents. 112 patterns across 11 categories — language, collections, streams, concurrency, and more — each with code comparisons, explanations, and curated documentation links. All generated from YAML content files by a JBang-powered Java build script.

From “Crypto AI” to general AI: Do AI agents dream of electric langoustines?

Mon, 23 Feb 2026 18:11:54 +0000

A Blade Runner riff for a world where the lobster ships paid endpoints while humans still argue about the roadmap.

The shift that matters for agent commerce - From “Crypto AI” to general AI

Today, you can search the web all day and never see an invoice.

That happens because you are not the paying client.

The commerce runs through ads, affiliate deals, and platform incentives, so results often optimize for who pays, not for what you asked for.

Stop Writing YAML: Automating Your Repo with Plain Natural Language

Fri, 20 Feb 2026 19:01:34 +0000

If you maintain a busy codebase, you already know the daily grind: triaging issues, writing status reports, updating documentation, and chasing down failed CI builds. What if your repository could handle that routine maintenance for you, using natural language instead of complex, fragile scripts?

You can even write in languages other than English!

In this week’s Rubber Duck Thursdays live stream, Cassidy Williams and I took a deep dive into GitHub Agentic Workflows . We explored how to move past deterministic if-then scripts and embrace “Continuous AI”, a world where your repository actually has the agency to understand context and safely execute tasks for you.

DevBcn, the developer's conference in Barcelona

Tue, 17 Feb 2026 09:56:33 +0000

Hola developers !!!!!

The 11th edition of DevBcn , the developer’s conference in Barcelona is coming next June. The perfect place to have great technology talks 🤖, perfect weather 🏖️, amazing food 🥘, and an unforgettable experience 💖.

It will be hosted on the 16th and 17th of June 2026, in the World Trade Center Conference Center , having 4 rooms with talks in parallel during the 2 days of the conference : Java/JVM, AI, Cloud, Frontend, Managing and Soft skills.

Enabling AI Agents to Use a Real Debugger Instead of Logging

Mon, 16 Feb 2026 21:12:13 +0000

Every Java developer has been there. Something breaks, and the first instinct is to litter the code with System.out.println(">>> HERE 1"). Then HERE 2. Then HERE 3 --- value is: " + x. Rebuild. Rerun. Stare at the console. Repeat.

We’ve been doing this for decades. And now, so have our AI agents.

When you ask an AI coding assistant to debug a Java application, it almost always reaches for the same playbook: add logging statements, recompile, rerun, read the output, and reason about what happened. It’s the println debugging loop, automated — but it’s still println debugging.

Windsurf AI and SonarQube The Dream Team for AI Code Quality

Mon, 16 Feb 2026 09:34:00 +0000

Hola! 👋 As a Java developer, you probably spend a good chunk of your day making sure your code doesn’t just “work,” but is also maintainable, secure, and reliable. I’ve been using a tool that is changing how I handle large projects: Windsurf.

It is an agentic IDE that understands what you are trying to do across your whole project. Let’s see why this is a game-changer for our Java workflows. 🚀

Join Our Webinar: Build Agents, RAG Pipelines and More

Tue, 10 Feb 2026 12:18:17 +0000

Build Agents, RAG Pipelines & Multi-Model Workflows — One API, Zero Lock-In

Modern enterprises want to move fast with AI—but juggling different providers, SDKs, formats, and deployment models quickly becomes complex and brittle.

That’s why we’re excited to announce our upcoming webinar:

Unlock Enterprise AI on the JVM: Build Agents, RAG Pipelines & Multi-Model Workflows with BoxLang AI One API, Zero Lock-In Led by Luis Majano

In this session, you’ll discover BoxLang AI , an open-source library that brings unified, fluent AI orchestration to the JVM ecosystem. With a single, intuitive API, BoxLang AI lets you integrate 12+ leading AI providers (including OpenAI, Claude, Gemini, Grok, Ollama, Groq, and more), switch models, or combine them into advanced workflows—without rewriting your code.

Machine Learning in Java - SPAM detection using ONNX

Tue, 10 Feb 2026 06:51:50 +0000

Believe it or not, it is possible to do Machine Learning in Java. In this article I go over how to implement a Spring Boot API for Spam Detection using an advanced anti-spam model from the Hugging Face onnx-community and Microsoft’s ONNX Runtime for Java .

We will package the API up as a Docker image which we can run a container from using docker or podman, and I guess in theory you could deploy on your Kubernetes cluster, if you (are) fancy.

JC-AI Newsletter #13

Thu, 05 Feb 2026 21:12:12 +0000

Two weeks have passed, and it is time to present a new collection of readings that may shape developments, utilization or ideas in the field of artificial intelligence in 2026.

While significant activity characterizes the AI field, many unresolved research, design, and implementation challenges continue to impact progress. Future advancement depends heavily on understanding the nature of these challenges to approach probabilistic problems from the appropriate directions. This JC-AI newsletter features insightful interviews with key figures in the field, enabling readers to ask the right questions and compare visions of an ‘uncertain future’ against current capabilities to maintain a grounded perspective.

FOSDEM 2026: Open Source Supply Chains, CRA Compliance, and the Future of Software

Mon, 02 Feb 2026 22:52:20 +0000

(a.k.a. “So… what did you do this weekend?”)

I’m back from four days in Brussels and the uniquely exhausting experience that is FOSDEM. Mentally fried. Physically wrecked. Entirely glad I went.

The Chaos and the Crowd

Around 8,000 people made the trip this year. Some arrived for the first time; many returned as annual pilgrims.

FOSDEM remains a strange outlier in the modern conference world: free to attend, no registration gatekeeping, and no sponsors dictating the tone. You just turn up.

Claude Code SonarQube MCP: A Java Developer’s Workflow

Mon, 02 Feb 2026 15:15:17 +0000

Hola Java developers! 👋

We all know the feeling. You are “in the zone,” coding away in your terminal, feeling like a hacker from a 90s movie. But then, reality hits. You need to check a rule, review a vulnerability, or verify if your project passes the quality gate.

What do you do? You Alt+Tab. You open the browser. You log in. You search. And just like that… the flow is gone. 📉

DocBox v5 - Reborn: Modern API Docs for BoxLang & CFML

Tue, 27 Jan 2026 12:15:45 +0000

Welcome to DocBox v5! We didn’t just update DocBox. We rebuilt it from the ground up.

DocBox v5.0.0 represents a complete architectural rewrite—modern syntax, blazing performance, and a stunning new look that finally brings API documentation into 2025. Gone are the clunky HTML pages of yesteryear. Say hello to a gorgeous, theme-driven single-page application that makes browsing your API docs feel like using a premium developer tool. We have also released a dedicated module for BoxLang: BX-DOCBOX. A fully interactive CLI tool for generating your docs from the command line using pure BoxLang.

Bring AI into your Jakarta EE apps with LangChain4J-CDI

Sat, 24 Jan 2026 17:20:02 +0000

Goal : This article will demonstrate how to add AI features to a Jakarta EE / MicroProfile application using LangChain4J‑CDI, with simple to implement examples that runs on Payara, WildFly, Open Liberty, Helidon, Quarkus or any CDI 4.x compatible runtime.

Note: This is an updated article to the one published on the JAVAPRO’s magazine - “04-2025 | Java 25 - Special Edition” . Since the release of LangChain4J-CDI version 1.0.0, there’s been minor changes, but the fundamental architecture and usage of the library is the same.

BoxLang AI v2: Enterprise AI Development Without the Complexity

Thu, 22 Jan 2026 15:09:25 +0000

One Year. 100+ Features. Unlimited Possibilities.

Just one year ago, in March 2024, we launched BoxLang AI 1.0. Today, we’re thrilled to announce BoxLang AI v2—a massive leap forward that positions BoxLang as one of the most powerful and versatile AI framework on the JVM. This release is 9-months in the making, with over 100 new features! This would have not been possible without all the new features that the BoxLang JVM language exposes to developers like: Server Side Events, HTTP Streaming, HTTP pooling, Caching, and so much more.

SonarQube AI Code Assurance & MCP: Auto-Fix Java (Part 4)

Mon, 19 Jan 2026 15:27:14 +0000

Hola Java developers! 👋

Welcome to the Grand Finale of our series.

Part 1 : We turned your IDE into a fortress.
Part 2 : We synced the team with Connected Mode.
Part 3 : We secured the Supply Chain (dependencies).

We have become excellent at finding bugs. But let’s be honest: Finding them is only half the battle. Who is going to fix them?

We are drowning in a backlog of “Technical Debt,” “Code Smells,” and “Security Hotspots.” You don’t have enough hours in the day to refactor every complex method or research the perfect fix for a regex denial-of-service vulnerability.

JC-AI Newsletter #12

Wed, 14 Jan 2026 07:15:44 +0000

F irst of all, Happy New Year 2026! This year is designated in the Chinese Calendar as the Year of the Fire Horse (starting on February 17.). The year 2026 brings not only tremendous energy to AI development but also, in my humble opinion, many breakthroughs in the field.

Although there have been many small steps toward the field’s evolution, it often feels that development is stagnating, applying known or slightly tweaked strategies to non-deterministic problems while expecting deterministic results. This includes the often misleading benchmarking strategies (deterministic) performed on synthetic datasets.

How to choose your LLM without ruining your Java code

Fri, 09 Jan 2026 19:49:47 +0000

Let’s be honest: when we try a new AI model, the first thing we look at is if the code compiles and does what we asked. But if you have been in the Java world for a while, you know that “working” is just level 1. The real final boss is reliability, maintenance and security. 💀

I have been analyzing the latest Sonar Leaderboard (with fresh data from late 2025/2026 on 4,444 tasks) and there are big surprises.

Not a Lucid Web3 Dream Anymore: x402, ERC-8004, A2A, and The Next Wave of AI Commerce

Fri, 09 Jan 2026 16:05:58 +0000

This article is for technically savvy readers, especially developers, protocol designers, and product teams working with AI agents, APIs, or crypto rails, who want a clear view of how these areas connect.
It explains how x402, ERC-8004, and agent discovery layers turn APIs and agents into small usage-based businesses, and what that means for real systems over the next 1–3 years.

Vocabulary for this article

In this article, I use the term micro business for a very small overall business, and nano business for a single x402-priced endpoint or agent that earns on its own from per-call payments in stablecoins.

AP2 (Agent Payment Protocol): AP2 defines how agents pay each other. It standardizes how a service quotes a price, how payment is confirmed, and how both sides record what was bought, so payments fit directly into automated agent workflows. In practice, it is a protocol that lets one machine pay another machine for work, without a human in the loop.

A2A (Agent-to-Agent communication): A2A covers how agents talk, pass context, and coordinate work. It lets agents call each other, exchange structured messages, and chain tasks instead of acting as isolated scripts.

x402: x402 is an HTTP-based payment protocol for APIs. A server responds with status 402 Payment Required, the price, and a payment route, and the client pays by using stablecoins on-chain and then retries the request to get the result.

ERC-8004 (8004): ERC-8004 standard is an on-chain registry for agents. It gives each agent an identity and a place to store reputation data, so other agents and tools can decide whom to trust and which services to call.

Foreword

x402 and ERC-8004 .

BoxLang Native Couchbase Module

Tue, 16 Dec 2025 08:37:02 +0000

Ortus Solutions is thrilled to announce the official release of bx-couchbase v1.0 , a groundbreaking module that brings native enterprise-grade Couchbase capabilities to the BoxLang language and ecosystem. Designed for modern distributed applications, bx-couchbase unifies high-performance caching, resilient distributed locking, and advanced AI vector memory—empowering developers to build scalable, intelligent, fault-tolerant systems with unprecedented ease.

Couchbase + BoxLang: A High-Performance Combination

Couchbase is more than a database—it’s a distributed NoSQL platform engineered for speed, flexibility, and global scale. With sub-millisecond key-value operations, built-in vector search, and multi-data-center support, it is the ideal foundation for next-generation AI-powered applications.

Foojay Podcast #86: Agents, MCP, and Graph Databases: Java Developers Navigate the AI Revolution

Mon, 15 Dec 2025 06:45:00 +0000

The AI revolution isn’t replacing Java developers. No, it’s forcing us to think harder.

Welcome to another episode of the Foojay Podcast! Today, we’re talking about AI and Java, how it’s changing the way we work, what we need to watch out for, and why understanding what’s really happening matters more than ever.

I recorded interviews at Devoxx and JFall and spoke with people who build and use this technology every day.

The End of One-Sized-Fits-All Prompts: Why LLM Models Are No Longer Interchangeable

Sun, 14 Dec 2025 18:48:31 +0000

For developers and product builders, one assumption has guided the last few years of LLM application development. To improve your product, just swap in the latest frontier large language model. Flip a single switch and your tool’s capabilities level up.

But that era is over. We’re now seeing that new models like Anthropic’s Claude Sonnet 4.5 and OpenAI’s GPT-5-Codex have diverged in fundamental ways. The choice of which model to use is no longer a simple engineering decision but a critical product decision. Flip that switch today… and the very texture of your product changes.

JC-AI Newsletter #11

Tue, 09 Dec 2025 16:12:01 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter explores the evolution of agentic AI systems, provides valuable insights into the Chain-of-Thought (CoT) approach, Vibe coding, and discusses the pattern-matching capabilities of LLMs. The newsletter features an insightful interview with Stuart J. Russell, known for his significant contributions to the AI field. Even more exciting is the published paper by Apple researchers titled ‘The Illusion of Thinking…’ and several immediate reactions to the authors’ conclusions, which allow newsletter readers to observe current research challenges and scientific community responses. This provides readers with a vital picture of the state-of-the-art in AI research.

The 5 Knights of the MCP Apocalypse 😱

Tue, 09 Dec 2025 15:55:41 +0000

Let’s talk about that new MCP (Model Context Protocol) Server your team is using to connect to your real data services. It’s awesome, right? It’s the “magic box” that gives your AI Agent access to the real world—live databases, internal APIs, and all your tools.

But here’s the catch: you don’t own the code. 🚫

It’s a vendor product, an open-source project, or another team’s platform. You can’t just change its code when you find a security hole, unless you have the code and recompile it and deploy it.

How CodeRabbit's Agentic Code Validation helps with code reviews

Sun, 07 Dec 2025 11:10:21 +0000

The 2025 Stack Overflow survey reveals a paradox: while 84% of developers express confidence in adopting AI tools, nearly half (48%) still distrust the accuracy of their outputs. This tension between optimism and skepticism has reshaped how teams think about quality assurance.

From PRD to PR in days (not weeks)

The bottleneck in software development has fundamentally shifted from writing code to validating it.

In the early days of AI-assisted development, the workflow was straightforward: AI suggested code, humans read the suggested snippet and then decided whether or not to accept that suggestion. Tab completion wrote boilerplate. Copilot suggested functions. But a senior engineer still manually validated and chose each line of code to ensure its quality, structure, and safety before making a pull request.

JC-AI Newsletter #10

Wed, 26 Nov 2025 18:39:40 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how agentic AI systems improve accuracy, tutorials on agentic system architecture, and importnat security challenges arising from increased not only from agentic AI systems adoption. This edition of the AI newsletter includes compelling discussions and interviews about the future of AI and approaches.

Navigating the Nuances of GraphRAG vs. RAG

Thu, 20 Nov 2025 21:28:52 +0000

While large language models (LLMs) hold immense promise for building AI applications and agentic systems, ensuring they generate reliable and trustworthy outputs remains a persistent challenge. Effective data management—particularly how data is stored, retrieved, and accessed—is crucial to overcoming this issue. Retrieval-augmented generation (RAG) has emerged as a widely adopted strategy, grounding LLMs in external knowledge beyond their original training data.

The standard, or baseline, implementation of RAG typically relies on a vector-based approach. While effective for retrieving contextually relevant documents and references, vector-based RAG faces limitations in other situations, particularly when applications require robust reasoning capabilities and the ability to understand complex relationships between diverse concepts spread across large knowledge bases. This can lead to outputs that disappoint or even mislead end-users.

Beyond Keywords: Hybrid Search With Atlas and Vector Search (Part 3)

Thu, 13 Nov 2025 13:56:23 +0000

Bringing together semantic vectors and exact keyword matching with $rankFusion

If you’ve been following along this series, you already know we started by giving our movie search app the ability to understand meaning—not just keywords—using semantic search, as discussed in Part 1: Implementing Semantic Search in Java With Spring Data . Then, we made it even smarter by adding filters and optimizing performance with embedding strategies in Part 2: Optimizing Vector Search With Filters and Caching .

JC-AI Newsletter #9

Wed, 12 Nov 2025 15:21:12 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how AI enhances productivity through enterprise studies, tutorial, agentic system architecture, GraphRAG, evaluating risk methodologies in agentic systems, and the security challenges arising from increased AI-LLM adoption. This edition of the AI newsletter includes a compelling discussion between six of the most influential leaders in artificial intelligence, along with additional content.

A Guide to SonarQube MCP Server on IntelliJ

Fri, 07 Nov 2025 17:00:24 +0000

Hey Java devs! 👋 Ever feel like you’re drowning in a sea of code, trying to keep it reliable,, efficient, and secure? We’ve all been there. Juggling new features, bug fixes, and pull requests is a daily grind. But what if you had an AI-powered assistant to help you out? That’s where the SonarQube MCP Server comes in. Let’s dive into how this cool new MCP can supercharge your daily coding routine. 🚀

JC-AI Newsletter: Easy Access to Expanding Challenges

Tue, 04 Nov 2025 18:13:33 +0000

A few months ago, I launched the AI Newsletter to provide a minimally biased perspective on the growing challenges surrounding artificial intelligence.

My primary motivation was and remains to be serving the community not only by showing how to use and access specific services for utilizing Large Language Models, but also by support a deeper understanding of the broader artificial intelligence landscape.

Many of the core challenges that have emerged around LLMs have not been and still not properly addressed, often omitted due to their uncomfortable implications.

Let's create an AI MCP server with Quarkus

Mon, 03 Nov 2025 10:15:45 +0000

Hey Java Devs, Let’s Talk About AI MCP! 🤖

Ever feel like your AI models are stuck in a bubble, cut off from the real-time data and tools they need to be truly useful? Well, you’re not alone! This has been a major headache for developers. But what if I told you there’s a new sheriff in town that’s changing the game? Enter the Model Context Protocol (MCP).

So, What’s the Big Deal with MCP?

Think of MCP as a universal translator for your AI. It’s an open standard that lets AI assistants, like large language models (LLMs), seamlessly connect with external data sources, tools, and just about any environment you can think of. No more building custom, one-off integrations for every single tool and data source. With MCP, you create a standardized way for your AI to talk to the outside world. Pretty neat, huh? 😉

JC-AI Newsletter #8

Thu, 30 Oct 2025 06:36:12 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how AI enhances productivity through enterprise studies, agentic system architecture, attack vectors, Model Context Protocol (MCP) implementation, Agent-to-Agent (A2A) protocol, Java code generation within IDEs, LLM benchmarking methodologies, and the security challenges arising from increased AI-LLM adoption.

The world influenced by LLM is changing very quickly, let’s start…

Beyond Keywords: Optimizing Vector Search with Filters and Caching (Part 2)

Thu, 23 Oct 2025 15:44:38 +0000

Enhancing precision with pre-filters and reducing costs with embedding caching

Welcome back! If you landed here without reading Part 1: Beyond Keywords: Implementing Semantic Search in Java With Spring Data , I recommend going back and checking it first so the steps in this article make more sense in sequence.

This is the second part of a three-part series where we’re building a movie search application. So far, our app supports semantic search using vector queries with Spring Data and Voyage AI. In this article, we’ll take things further:

How Chat Memory Manipulation Can Ruin Your AI System

Thu, 16 Oct 2025 10:45:59 +0000

Do LLMs have any conversational memory?

With the use of ChatGPT, Claude, and Copilot, we are now quite used to chat-based AI assistants that can help us. We’ve all grown accustomed to chatbots that “remember” us and the conversation we had before.

From virtual assistants that recall our preferences to support bots that track our past issues, chat memory feels like a natural part of interacting with digital agents. It’s easy to assume that modern AI models like ChatGPT or other LLM-powered bots possess similar built-in memory.

7 habits of Highly Effective Java Coding

Wed, 15 Oct 2025 11:25:03 +0000

From AI User to AI Pro

Let’s be real, AI coding tools are everywhere now. 🤖 They’re no longer some shiny new toy—they’re a part of our daily grind as developers, just like our morning coffee. ☕

For us Java devs, whether we’re wrestling with a giant legacy app or juggling a bunch of microservices, these tools look like a huge win for getting stuff done faster. 🚀

But here’s the catch: just coding faster isn’t the whole story. If you’re not careful, it can actually lead to bigger problems down the road. 🤔

JC-AI Newsletter #7

Tue, 14 Oct 2025 05:35:01 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on Hallucination, Java Code Generation, Testing, Agentic System Architecture and LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

Keywords Meet Vectors: Hybrid Search on MongoDB

Thu, 09 Oct 2025 14:49:49 +0000

In the previous issues, I explained how to run a local MongoDB Atlas cluster using Atlas CLI , what vector search is, and how to use it . Now, let’s take a closer look at hybrid search.

Reading time: 4–5 min

What is hybrid search?

Hybrid search in MongoDB brings together two complementary search techniques:

Full text search (BM25 via Atlas Search )—optimized for exact keyword matches, powered by Lucene inside mongot. Perfect when users expect documents that literally contain their query terms.

Vector search (kNN via Atlas Vector Search )—optimized for semantic similarity. It uses dense embeddings from ML models to find conceptually related content, even when no keywords match.

On their own, each method has advantages and limitations. Text search misses context (“non-linear crime story” won’t return Memento). Pure semantic search may return results that are semantically aligned but sometimes not practically useful. Hybrid search combines the strengths of both, ensuring results are contextually relevant and precise.

Agents Meet Databases: The Future of Agentic Architectures

Thu, 02 Oct 2025 15:01:49 +0000

With 2025 hailed as “the year of agents” by NVIDIA CEO Jensen Huang and OpenAI CPO Kevin Weil , AI agents are increasingly of interest to organizations across industries. These autonomous systems will often need to interact with databases, where much of the world’s valuable data resides. According to IDC’s Data Age 2025 report , enterprises will manage nearly 60% of the world’s data by 2025, most of it organized in databases. As a result, databases will be central to agentic architectures, and the success of agent deployments will depend on how well they connect and interact with them.

JC-AI Newsletter #6

Wed, 01 Oct 2025 17:18:16 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond opinion pieces and Java focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on Hallucination, Security, RAG and LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

Building an AI Semantic Movie Recommender with Vector Search

Tue, 30 Sep 2025 13:23:18 +0000

Last time, we created a vector search index in a local MongoDB Atlas cluster . Now, let’s put it to work with a real case: building an AI-powered movie recommender that suggests films similar to The Matrix–without any shared keywords.

🕒 Reading time: 3-4 min

🎯 The challenge

This demo will be entirely based on the pre-generated vector embeddings already stored in the sample_mflix dataset—no API calls and no new model runs. Everything will remain local. If you haven’t done it yet, learn how in this article 👉 Loading embeddings into MongoDB

Payara Server Maven Plugin + AI Agent

Tue, 30 Sep 2025 08:43:20 +0000

Managing Payara Server Just Got Smarter

Imagine managing your Jakarta EE applications not just with Maven goals, but by asking natural questions.

With the experimental AI Agent built into the Payara Server Community’s Maven Plugin, you can now query server internals and perform admin tasks using plain English — directly from the same terminal where you build and deploy your applications.

Thanks to this integration, developers can inspect, query and even execute server commands using natural language. It’s a powerful and intuitive way to interact with Payara Server — no need to remember long command syntax or dig through documentation.

Power your AI application with Vector Search

Tue, 23 Sep 2025 16:23:37 +0000

Most major database vendors, like MongoDB , are adding vector search capabilities to their products. It’s becoming a standard feature as demand for AI-powered applications grows.

🕒 Reading time: 3-4 min

🧠 What is vector search needed for?

MongoDB Vector Search enables semantic queries. For example, finding support tickets with similar meanings even if they use different words. It also powers hybrid search by combining exact keyword matches like “error 500” with semantically similar phrases like “server failure”. Another use case is personalization, such as recommending articles similar to those a user has read.

JC-AI Newsletter #5

Thu, 18 Sep 2025 07:19:33 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond opinion pieces and Java focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

Research: Measuring Energy Consumption in Programming Languages for AI Applications

Mon, 15 Sep 2025 07:03:00 +0000

Decades ago, I contributed to a very interesting project called SunSPOT at SUN Microsystems. It was a small device with wireless connectivity, built-in sensors, running on Java (compatible with runtime 1.6), and powered by battery. It enabled the design of small applications and the connection of additional hardware, or simply the utilization of available sensors. Later, together with Markus Hirt, we created the Robo4j framework . A small and lightweight Java framework that enables rapid assembly of robots or other IoT systems (JDK 21+). In Robo4j, we primarily used thePi4j project for handling I/O operations on the Raspberry Pi platform with drivers created for specific hardware.

Stochastic AI Agility: Breaking Cycles of Debt

Wed, 10 Sep 2025 11:27:16 +0000

The launch of ChatGPT in November 2022 has significantly influenced and potentially transformed industry standards across multiple sectors. While my primary focus remains on the information technology sector, observations indicate that its impact extends across all industries and affects the daily lives of consumers and professionals alike.

This article examines the observed changes in project management practices. These observations are govern by Role 17: Stochastic AI Agility. Over past two decades, the industry has actively pursued the implementation of agile methodologies to enable iterative product delivery.

Spec-Driven Development with AI: A New Approach and a Journey into the Past

Mon, 08 Sep 2025 07:35:46 +0000

The software development world is buzzing about AI-assisted coding. Tools like Claude Code, Windsurf, and JetBrains Junie promise to make us more productive. But most approaches focus on generating code faster – they’re still code-centric.

What if we took a different approach? What if we made requirements the source of truth and let AI handle everything downstream?

After years of building business applications, I began developing a methodology that combines ideas from the Rational Unified Process (RUP) with modern AI tooling: The AI Unified Process . The results are remarkable: better business alignment, maintainable code, and complete traceability from business needs to implementation.

JC-AI Newsletter #4

Tue, 02 Sep 2025 20:27:52 +0000

14 days have passed and it’s time for a new batch of readings that could shape developments in the field of artificial intelligence.

The current newsletter vol. 4 offers us a closer look at several different areas of artificial intelligence. We start with the topic of energy consumption and the environmental impact of systems serving artificial intelligence, and continue with automation, how we obtain data for RAG, robustness of GenAI systems, vibe-coding and more.

AI4Devs - Schedule published

Mon, 01 Sep 2025 20:05:04 +0000

The wait is over—AI4Devs Amsterdam has just published its official schedule, and it’s packed with talks that every developer working with (or curious about) AI will want to catch.

From live coding sessions to hands-on workshops, from security insights to multi-agent architectures—the program is designed to keep things practical, technical, and deeply relevant.

Whether you’re already building AI-powered systems or just starting to explore what’s possible, this year’s edition has something for you. Let’s take a look at the highlights.

JC-AI Newsletter #3

Tue, 19 Aug 2025 08:06:34 +0000

The first and second newsletters introduced a 14-day cadence, and even though it is the holiday season for many of us, we are sticking to the promised period.

The current newsletter vol.3, brings a collection of valuable articles focusing on challenges that are commonly reported through reported breakthroughs in the field of artificial intelligence. Although some articles may remain open or contain suggestions for future research due to the intensive development and utilization efforts of agentic AI systems, these articles can be considered valuable to the community, increasing awareness and understanding of ongoing challenges.

New Java Benchmark for Coding LLMs puts GPT-5 at the top

Mon, 18 Aug 2025 08:06:40 +0000

The Brokk Power Ranking is a new open-source coding benchmark , featuring 93 tasks from large, real-world codebases. You can check out the current Power Ranking here .

SWE-bench is the closest thing we have to a standard, objective benchmark for LLM coding performance, but it has a bunch of issues, the largest of which are that it’s Python-only, and it’s old enough that almost certainly some labs are now training to the test. (Epoch AI has a great writeup on the more subtle problems with SWE-bench if you want to go deeper.)

Do we understand the value of AI knowledge ?

Tue, 12 Aug 2025 11:26:49 +0000

I remember the first time I saw a diagram of a neuron (Img.1.). I was a school kid, and among other hobbies, I was interested in the human brain, it fascinated me. I borrowed a book from the bookstore to find out how it all worked, because these cells are responsible for more than just the functioning of the human species.

Img.1.: Anatomy of multipolar neuron{#caption-attachment-117093}

Simplification of neuron, perceptron

I took a university course focused on neural networks and their applications, basically research, in engineering and control systems. It was a lot of fun because the neuron was simplified into an abstraction presented as a perceptron (Img.2.).

Semantic Caching with SpringBoot & Redis

Thu, 07 Aug 2025 06:58:07 +0000

TL;DR: You’re building a semantic caching system using Spring AI and Redis to improve LLM application performance.

Unlike traditional caching that requires exact query matches, semantic caching understands the meaning behind queries and can return cached responses for semantically similar questions.

It works by storing query-response pairs as vector embeddings in Redis, allowing your application to retrieve cached answers for similar questions without calling the expensive LLM, reducing both latency and costs.

JC-AI Newsletter #2

Tue, 05 Aug 2025 06:30:03 +0000

The JC-AI Newsletter Vol.2 brings again a very interesting collection of articles worth considering.

The world influenced by LLM is changing very quickly, let’s start…

article: OpenAI CEO Sam Altman warns of an AI ‘fraud crisis’

author : Clare Duffy, CNN
date : 2025-07-22
desc.: Sam Altman discusses the serious potential for current AI abuse. Although the example of attacks on financial institutions is mentioned, Sam Altman warns of the broader impact before one even takes advantage of LLM agent systems.

AI Applications with LangChain4j Guardrails and Spring Boot

Tue, 29 Jul 2025 11:16:31 +0000

As AI applications become increasingly complex, ensuring that language models behave predictably and safely is paramount. LangChain4j’s guardrails feature provides a powerful framework for validating both the inputs and outputs of your AI services.

This article demonstrates how to implement comprehensive guardrails in a Spring Boot application, with practical examples that you can adapt to your use cases.

📦 Complete source code available at : github.com/rokon12/guardrails-demo

Understanding LangChain4j Guardrails

In LangChain4j, guardrails are validation mechanisms that operate exclusively on AI Services, the framework’s high-level abstraction for interacting with language models. Unlike simple validators, guardrails provide sophisticated control over the entire AI interaction lifecycle.

CodeRabbit Tutorial for Java Developers

Mon, 28 Jul 2025 12:43:19 +0000

CodeRabbit is an AI-powered code review tool that integrates seamlessly with your Git workflow to provide intelligent, automated code reviews.

For Java developers, CodeRabbit offers specialized analysis that understands Java syntax, best practices, and common patterns.

Getting Started

Prerequisites

A GitHub, GitLab, Azure DevOps, or Bitbucket repository.
Java project with standard structure (Maven or Gradle).
Admin access to your repository.

Setup Process

Install CodeRabbit
- Visit CodeRabbit.ai .
- Sign up using your credentials, while noting that CodeRabbit is free for OSS, supports GitHub, GitLab, Azure DevOps, and Bitbucket.
- Grant necessary permissions to your repositories.
Repository Configuration
- Select the Java repositories you want CodeRabbit to review.
- CodeRabbit automatically detects Java projects and configures appropriate rules.
Initial Setup Verification
- Create a test pull request with a simple Java change.
- Verify CodeRabbit comments appear within minutes.

Core Features for Java Development

1. Code Quality Analysis

CodeRabbit analyzes your Java code for:

AI Newsletter #1

Tue, 22 Jul 2025 05:39:26 +0000

There is a lot going on in today’s technological world, but the most intense and vibrant area is undoubtedly the field of artificial intelligence. After brainstorming, our Java Champion Education group agreed to create a newsletter with a 14 days cadence. In our newsletters, we will include a collection of recently read interesting resources in the field of artificial intelligence with a short description.

Although the stream of published articles is very large and the ability to read them all is an illusion, the published selection, such as the below is implicitly narrowed. The purpose of the AI Newsletter is to help everyone stay informed and expand their knowledge in areas related to artificial intelligence.