Code got cheap. Making software didn't.
My friend Markus Eisele put it in one line: code is cheap now, software isn't. Until recently, both were expensive, so the gap stayed hidden. Now you just get to the expensive part faster. Writing…
category
AI
37 posts
Your Agent Needs to Read Before It Writes
A few months ago I asked an AI agent to write some Quarkus code for me. The code came back, and it worked. It compiled, it booted, it answered. If the bar were "it works",…
Everyone Says "Context Engineering," But Thousands of Repositories Say AGENTS.md
Eight configuration mechanisms exist for agentic coding tools. A team of researchers went looking for them in 2,853 GitHub repositories, and what came back is one mechanism carrying almost all the weight. The paper is…
Quarkus 3.37.0.CR1: extensions start teaching the AI coding agent
The release notes for Quarkus 3.37.0.CR1 read like a busy week. A wave of entries adds an "AI skill" to specific extensions, including `quarkus-quartz`, `quarkus-hibernate-reactive`, `quarkus-redis-cache`, and `quarkus-security-jpa`. One line introduces the ability to get…
LangChain4j Brings the Blackboard Pattern to the JVM
The LangChain4j 1.16.0 release notes carry a line that should make anyone running a multi-agent system on the JVM stop scrolling: Introduce Blackboard agentic pattern. Until now, when you wanted agents to coordinate in LangChain4j,…
OpenJDK Won't Accept AI-Generated Code: What's Actually Going On
Recently there was a decision in the Java world that left a lot of people unhappy. The OpenJDK maintainers decided they will not accept contributions of AI-generated code. Before we react to it, let's understand…
Crash Recovery for Agentic Workflows in LangChain4j: What Gets Persisted, and Where to Put It
A multi-step agentic workflow is a stateful process. One agent validates an order, another waits on a human decision, a third finalizes it; each step reads and writes shared state, and the whole run can…
ClawRunr: when a Java AI agent belongs in your scheduler
JobRunr shipped ClawRunr, an open-source Java AI agent that runs on your own hardware and executes scheduled, recurring, and one-off background tasks. The part worth an architect's attention is where the agent lives: inside the…
The MCP Java SDK as an Anti-Corruption Layer
There is a tempting way to read the arrival of the Model Context Protocol Java SDK: as one more client library to bolt onto a service. Add the dependency, expose your existing services as tools,…
Agentic products at scale: what the demo hides
Recently, I sat in on a talk at StartSe AI Festival 2026 that stayed with me for days. On stage was Isabella Piratininga, iFood's Director of Technology and Innovation, and the subject was building agentic…
Day 2 at StartSe AI Festival 2026: notes for software engineers
As mentioned in my previous post, I'm in São Paulo this week for the StartSe AI Festival 2026 (May 13 and 14, at Pro Magno Centro de Eventos). For those joining now: this is the…
Day 1 at StartSe AI Festival 2026: notes for software engineers
I'm in São Paulo this week for the StartSe AI Festival 2026 (May 13 and 14, at Pro Magno Centro de Eventos). Context for those reading from outside Brazil: this is the largest AI gathering…
Tokenmaxxing: When Burning AI Tokens Became a Performance Metric
There's a term making the rounds that you should know: tokenmaxxing. It describes engineers competing to burn AI tokens under employer-imposed usage metrics. The concept exposes something structural about how companies measure AI adoption. Here's…
Quarkus LangChain4j 1.9.x: first-class MCP, Skills, and Neo4j for enterprise agents on Java
Three things landed in the enterprise plumbing in the past few weeks. At Knowledge 2026 (May 5), ServiceNow announced Action Fabric, an open MCP (Model Context Protocol) server, building on top of the Now Assist…
Java developers should pay attention to JetBrains Air
A lot of AI coding demos look impressive for about five minutes. Then reality shows up. Reality is the old service nobody wants to touch on a Friday afternoon. Reality is the module with naming…
Context Engineering: the role beyond Prompt Engineering
LLM is CPU. Context window is RAM. Andrej Karpathy captured something real with that analogy: the model processes, but the context is where information lives. What the model can reason about is bounded by what…
How to put coding agents under control in Java teams
A few years ago, if you told a Java team that an AI tool could open a pull request, a lot of people would treat that as the finish line. To be honest, I never…
LangChain4j Gives Java Teams a Practical AI Stack
A few days ago, I was reviewing what has actually changed in the Java plus AI ecosystem lately. Not the hype, but the pieces that help a team move from a nice demo to something…
LangChain4j + Quarkus: Building AI-Powered Java Services
Most Java teams do not need to switch to Python to integrate AI into their applications. If your stack already includes Spring Boot, Quarkus, or Micronaut, you have a clear path to add AI capabilities…
Why Java Dominates Enterprise AI
Artificial intelligence is now a production concern, not a lab experiment. Enterprise teams are no longer asking whether they should use AI. They are asking how to ship AI features that are secure, maintainable, cost-aware,…
How Project Panama Makes Native Code Safer and Simpler to Use in Java (for AI too)
Enterprise Java still forms a substantial portion of the software backbone behind global finance, logistics, and commerce. It is a mature ecosystem built around mission critical systems where stability, scalability, and reliability are not aspirational…
Java Engineering in the AI Era with Project Babylon and HAT
The landscape of enterprise software development is undergoing a structural shift, as artificial intelligence and high performance computing move to the center of strategic decision making in large organizations. For decades, Java has served as…
Building Your First AI Service with Quarkus, LangChain4j, and Ollama
* * The real value of AI in the enterprise lies in what an application can do. Integrating Large Language Models (LLMs) into Java applications is no longer a complex task. With Quarkus and LangChain4j,…
Building a Web-Searching Agent with Ollama, Langchain4j, and Quarkus
Running Large Language Models (LLMs) locally with tools like Ollama is a paradigm shift for developer productivity. It creates a sandbox for innovation, enabling rapid prototyping, offline development, and limitless experimentation without the friction of…
The Universal Adapter for Enterprise AI: Mastering the MCP with Quarkus and Langchain4j
The conversation around Generative AI has been dominated by what Large Language Models (LLMs) know. Their ability to process vast amounts of text and answer complex questions is impressive, but for any enterprise, knowledge alone…
Building a Local-First AI Knowledge Base with Quarkus, Langchain4j, and Ollama
Every established company faces a common, persistent challenge: its most valuable asset, its collective knowledge, is often fragmented and difficult to access. Technical documentation, project histories, HR policies, and architectural decisions are scattered across Confluence,…
How to Send Emails with an AI Agent: A Quarkus and Langchain4j Tutorial
This tutorial provides a step-by-step guide on how to build a Java application that can send emails based on natural language commands. We will create an AI agent using Quarkus and Langchain4j, equipping it with…
The $40 Billion AI Illusion: Why 95% of Projects Fail and The Opportunity for Java Developers
Despite a staggering $30-40 billion in enterprise investment into Generative AI, a recent report from MIT's Project NANDA reveals a shocking truth: 95% of organizations are getting zero return. This is not a minor hiccup…
From Automation to Autonomy: 7 Agentic AI Use Cases for Enterprise Java Developers
For decades, the world of enterprise Java has been about mission-critical systems, large distributed architectures, and the constant pressure to innovate while keeping everything stable. The business logic that powers global finance, logistics, and commerce…
OpenAI Went Open Source: What gpt-oss Means for Your AI Development Plans
The history of technology is marked by pivotal moments, shifts in strategy from major players that redefine the landscape for everyone. For years, the name OpenAI has been synonymous with the frontier of artificial intelligence,…
The Modern Java Stack for Agentic AI: Quarkus and Langchain4j
The way technology changes often follows familiar patterns. The jump from static, information-only HTML pages in the early 1990s to dynamic, interactive web applications was a huge shift. It turned the web from a passive…
10 Enterprise AI Use Cases Java Developers Are Ready To Build Today
The world of software development is buzzing with Artificial Intelligence, and it’s easy to get lost in the noise. Headlines are full of stories about AI models writing code, creating art, and changing the rules…
Java’s AI Sweet Spot: Skip Model Training with RAG and LangChain4j
For the enterprise Java developer, the most important decision in the AI era is not about which framework to learn, but where to focus your efforts. There is a lot of hype about model training,…
The $18 Trillion Engine: Why Java Still Runs the Enterprise (And Your Career), Even In the AI Era
Developers face constant pressure from hype. Every new framework promises to change everything. If you write Java, you might feel your skills are losing value. That view misses the economic facts underneath the world's software.…
The Enterprise AI Playbook for Java Devs: Master Integration, Not Data Science
If you are a Java developer working in the enterprise space, you are probably in one of two situations right now: you are either feeling intense pressure from management to "do AI," or you are…
The Java Developer's Shortcut to Building Production-Ready AI Applications
Feeling like your Java applications are stuck in the past while the AI revolution is happening now? You see the power of Large Language Models (LLMs), but integrating them into enterprise Java seems complex, slow,…
Why Java Powers Enterprise AI: Scalability, Security & Cloud-Native Leadership
Artificial Intelligence is no longer a futuristic concept or a research initiative. In 2025, AI is deeply embedded into enterprise systems across industries like finance, healthcare, logistics, and government. And while many associate AI development…