Topic
9 articles found
Stop Blocking Virtual Threads: Building Asynchronous Human-in-the-Loop AI Agents with Spring AI In 2026, letting autonomous AI agents execute high-risk enterprise tools without human oversight is a production liability, but blocking platform threads—or even Project Loom’s virtual threads—for hours w
Introduction: Modern LLM-powered applications require external tools to interact with real-systems such as a databases, APIs, cloud platforms, and enterprise services. MCP (Model context Protocol) provides standardized mechanism for exposing tools to AI agents. In this article, we will build an MCP
Stop Burning Cash on Long-Context RAG: Ephemeral Prompt Caching with Spring AI and JTokkit If your enterprise RAG pipeline is processing megabytes of legal documents or codebase context, you are likely burning thousands of dollars daily on redundant input tokens. Ephemeral prompt caching can slash t
This week's Java roundup for May 18th, 2026, features news highlighting: GA releases of WildFly 40, Micronaut 5.0, Maven Embedded GlassFish Plugin 8.0 and Apache Fory 1.0; the May 2026 edition of Open Liberty; point releases of Gatherers4j, Apache and Kafka; and the seventh milestone release of Spri
Most Spring AI tutorials jump straight to code. You copy the dependency, paste the config, call ChatClient, and something works. But when you need to actually build something — a chatbot that remembers conversations, an API that answers questions from your own documents — you hit a wall. Because you
Retrieval-Augmented Generation (RAG) is a powerful design pattern that allows you to ground Large Language Models (LLMs) with your proprietary, real-time context. This prevents hallucinations and eliminates the need for expensive model fine-tuning. Before touching Java code, you need to set up the i
This week's Java roundup for May 4th, 2026, features news highlighting: OpenJDK JEPs targeted for JDK 27; the sixth milestone release of Spring AI 2.0; the first milestone release of Grails 8.0; the first alpha release of Groovy 6.0; a point release of JobRunr; maintenance releases of GlassFish, Tom
MCP becomes especially interesting when it connects AI agents to systems that already exist in enterprise applications. For Java teams, Spring AI is one practical way to build that bridge. An MCP server exposes tools or data sources to AI clients through a shared protocol. Instead of wiring every AI
This week's Java roundup for April 27th, 2026, features news highlighting: OpenJDK JEPs for JDK 27; the fifth milestone release of Spring AI 2.0; the second milestone release of GlassFish 9.0; point releases of Quarkus, JReleaser, Gradle, LangChain4j and Google ADK for Java; the second beta release
