LLM on foojay.io - Friends Of OpenJDK

Can You Explain the Diff Your AI Agent Just Wrote?

Tue, 15 Sep 2026 14:12:01 +0000

Every Java developer has been in a code review where the question is simple: “What does this method do?”

The answer used to tell you something. The developer who wrote it would describe the intent, the edge cases, the trade-off they considered and rejected. The code review was a conversation about the invariant the code protects.

Now the answer is sometimes: “The agent wrote it.”

The code compiles. The tests pass. The linter is clean. Nobody in the review can explain the architecture of the PR, including the person who submitted it.

One Base URL, Many Coding Agents: What an OpenAI-Compatible Gateway Looks Like From java.net.http

Wed, 09 Sep 2026 16:09:53 +0000

Somewhere in every coding agent there is an HTTP client. Claude Code, Codex, Cursor, Cline, OpenCode: strip away the terminal UI or the editor pane and each of them serializes a conversation into JSON, POSTs it to a base URL with an API key in a header, and streams the answer back. The client owns the prompt assembly, the tool loop and the rendering; the model sits on the far side of that socket.

Debugging Is Invariant Discovery: What One Kafka Session Taught Us About AI Agents

Tue, 08 Sep 2026 14:14:36 +0000

Every Java team has a sentence like this one somewhere:

Any operation on a TID must go through the single asynchronous path and must not let TMS and EMV drift apart.

It is the kind of rule that is obvious once said and invisible until then. A terminal ID (TID) in a payments system, an asynchronous pipeline that updates two downstream systems, and the requirement that the two never disagree. Nothing in the type system enforces a rule like that, and no single class owns it. Rules of this kind live between consumers, services and stores.

“Commit created” — but it isn’t: why the agent’s word needs external verification, and what the mistake costs

Tue, 08 Sep 2026 08:54:03 +0000

A detailed report reads like proof. The agent lists the files it touched, names the branch, quotes a commit hash, adds a test count and closes with “done”. The work has a shape. The shape looks right. You have six more tickets.

The report is model output. The commit, if it exists, lives in .git. The file, if it exists, lives on disk. The build result lives in a process exit code and a run log. The chat window is none of those places, and it can only vouch for itself.

Did Your AI Agent Run the Debugger? One JVM Bug, Two Agent Runs

Thu, 03 Sep 2026 13:48:32 +0000

Java developers reach for the debugger without thinking about it. Set a breakpoint, run the failing test, look at the variables, then decide what to change.

Most AI coding agents I have watched skip that step. They read the stack trace, read the source, and propose a patch. The reasoning can look excellent and still be a guess about a program nobody ran.

I wanted to know what that guess costs. So I took one real JVM bug, one model, one prompt, and ran it twice with two debugging workflows. Here is what the two transcripts show.

Introducing BoxLang AI Explorer: A Local Catalog for Every AI Pattern

Tue, 18 Aug 2026 14:15:48 +0000

Learning a new AI API usually means jumping between scattered documentation pages, guessing at imports, and copy-pasting code that may or may not still work. We wanted something better for BoxLang AI, so we built the BoxLang AI Explorer : a local, browser-based catalog of runnable BoxLang AI examples, organized by category and difficulty, each with guidance, source code, and sample output. You can also try it online at https://ai.boxlang.io/explorer/

Build Secure AI Chat Applications with BoxLang, RAG, Ollama, and Amazon Bedrock with Dan Card

Thu, 13 Aug 2026 14:52:13 +0000

Build Secure AI Chat Applications with BoxLang, RAG, Ollama, and Amazon Bedrock

AI demos are everywhere. Building an AI-powered feature that can securely work with your documents, databases, and real application data is a very different challenge.

How do you give an AI model access to the right information without exposing sensitive data? Should you use a locally hosted model or a cloud service? How do you move beyond a basic chatbot and build something genuinely useful for your users or organization?

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.

Context Is Code: A Tour of APM and AgentRC

Fri, 05 Jun 2026 08:35:05 +0000

Context Is Code: A Tour of APM and AgentRC

If you’ve shipped an AI agent into a real codebase in the last twelve months, you’ve felt this: every agent, every developer, every machine — different setup. A README that says “install these extensions.” A copilot-instructions.md somebody copy-pasted from another repo. MCP server configs in three different files. The same skills duplicated for Copilot, Claude, Cursor, and Codex.

No version pinning.

Tiberius: A Security Testing Framework for LLM Applications in Java

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

Tiberius: A Security Testing Framework for LLM Applications in Java

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

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.

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.

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. 🎯

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.

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.

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 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.

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.

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?

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

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

x402, ERC-8004, A2A, and The Next Wave of AI Commerce: Do AI Agents Dream of Electric Langoustines?

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.

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. 🚀

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.

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.

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 .

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.

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.