This content introduces llm4j, a new Java-native framework designed for building production AI agents, challenging the Python-first assumption in the AI ecosystem. It provides JVM performance, type safety, Spring Boot integration, and an innovative orchestration DSL called Loom for multi-agent coordination.
This content discusses Java command-line debugging with AI agents, arguing that visual debuggers are a bottleneck in the era of agentic coding. It explores the need for a command-line debugging tool, such as jdb, that can be effectively used by AI agents.
This article describes the successful integration of the OpenAI API into a Spring Boot Java application, overcoming common challenges. It details the setup, error handling, performance optimization, and common mistakes for utilizing AI features.
This content introduces MCP (Model Context Protocol), a standard enabling AI agents to discover and call external tools over HTTP, simplifying integration. It's presented as a practical solution for Java developers, with real-world examples from a microservices production system.
The author felt existing AI agent conversations were too narrow and built Agentican, an open-source Java multi-agent framework. This framework aims to enable an AI-native workforce capable of handling complex, multi-step tasks and coordinating with each other.
The text discusses using Cursor AI with Java, emphasizing that applying specific rules is crucial to generate enterprise-grade code, moving beyond tutorial quality. It promises to present 8 production-tested rules for Java, covering Spring Boot, Maven, error handling, and more.
This article critiques using `CompletableFuture.allOf()` for orchestrating AI agent tool calls, citing issues like silent failures, resource leaks, and unhandled exceptions. It argues that even with Claude 3.7's advanced capabilities, robust AI agent development requires a stronger, more resilient orchestration layer beyond standard async patterns.
This document outlines how to build AI agent systems in Java for healthcare data solutions, leveraging libraries like DJL and Spring AI. It details the initial setup of a Maven project with the necessary dependencies to begin developing intelligent agents.
The author recounts the challenging 2.5-month journey to create NOVA, India's first Java-powered cross-device personal assistant, capable of controlling both laptop and phone. Initially abandoned, the project was revived with the help of ChatGPT for architecture and GitHub Copilot for coding, leading to its successful completion.
AWS has generally available the Spring AI AgentCore SDK, simplifying the development of production-ready Java AI agents. This SDK collapses weeks of infrastructure work for agentic AI into a single annotation, handling aspects like scaling, reliability, and memory repositories.
A Java developer aims to navigate the AI world while staying true to the language, aspiring to connect with peers, improve writing skills, and gain an edge in artificial intelligence. He perceives Java as refreshing itself and offers his perspective to fellow developers.
The content explains how a simple integer operation can lead to unpredictable results in concurrent programming due to race conditions. It illustrates with a Java example where non-atomic read-modify-write operations on shared state cause an incorrect final value.
This content debunks the myth that Java and JavaScript pass objects by reference, clarifying that both languages are strictly call by value. It explains that while object mutations within a function affect the original due to shared memory addresses, reassigning the parameter variable only changes its local copy.
This article examines the evolution of Capa-Java after one year, noting its shift from a "write once" paradigm to "configure once everywhere". It highlights a transformation in software development approach.