Every deterministic workflow step does not need a planner call.

This piece shows how to keep MCP tools boring inside a LangChain4j graph: one Quarkus MCP server, one workflow app, /topology, and tests that hit real Ollama instead of stubs.

https://www.the-main-thread.com/p/quarkus-langchain4j-mcp-tool-agents

#Java #Quarkus #LangChain4j #MCP

Agent demos love static diagrams. Production gives you a different graph.

This post shows how to expose a live LangChain4j topology from Quarkus with AgentMonitor, HtmlReportGenerator, and an SSE feed for recent runs.

https://www.the-main-thread.com/p/quarkus-langchain4j-topology-http

#Java #Quarkus #LangChain4j #Observability

Agent names are not a routing strategy.

This walkthrough builds a Quarkus + LangChain4j sample that uses filesystem Skills to make ownership explicit, keeps a baseline supervisor for comparison, and proves the routing with HTTP tests.

https://www.the-main-thread.com/p/agent-skills-quarkus

#Quarkus #LangChain4j #Java #AIEngineering

Once a tool-calling assistant grows from 5 tools to 50, the problem stops being “prompting” and starts being context geometry.

This walkthrough builds a Quarkus + LangChain4j + Ollama example and shows what tool search actually changes: smaller working sets, visible search rounds, and more prompt headroom even when local latency is messy.

https://www.the-main-thread.com/p/langchain4j-tool-search-quarkus-ollama

#Quarkus #LangChain4j #Ollama #Java

Still building #AI with one model per request? You’re already behind. @kevindubois & Laura Cowen map the shift to agentic systems & why orchestration beats prompts.

Ready to design real AI architectures? Dive in: https://javapro.io/2026/03/31/agentic-ai-patterns-for-enterprise-software/

#Java #LangChain4j @langchain4j

In this #InfoQ article, Vignesh Durai explains how agentic and multimodal AI systems can be engineered using #ApacheCamel & #LangChain4j.

The solution combines LLM-based reasoning, retrieval-augmented generation (RAG), and image classification.

🔗 Read now: https://bit.ly/4sXdlcM

#AI #LLMs #DataPipelines

Tomorrow I’m speaking at the Bangalore JUG Special Talk on Open-Source GPU-Powered Image Generation with LangChain4j. We’ll walk through a Java-based stack using Spring, LangChain4j, ONNX Runtime, CUDA, and SD4J to build a cloud-ready image generation service with monitoring and a real-time UI.
RSVP: https://www.meetup.com/bangalorejug/events/314000765/

#Java #AI #LangChain4j #OpenSource #GPU

Exclusive Devoxx UK Discount for Quarkus Devs!

Want to catch all the supersonic, subatomic Java talks at Devoxx UK? Grab £50 off your registration with the exclusive code DVX26QUARKUS.

Don't miss the Quarkus sessions, and be sure to drop by the Quarkus Community Booth. Let's talk high-performance, cloud-native apps, and our latest Generative AI integrations with LangChain4j.

See you in London!

#DevoxxUK #Quarkus #Java #AI #LangChain4j #OpenSource #quarkusworldtour

Cheerio, London! The Quarkus community is heading to Devoxx UK on May 6th and 7th!

We are proud to sponsor a booth at this year's event in the Business Design Centre. Stop by to chat with our community members about how to supercharge your skillset with supersonic, subatomic Java. We'd love to talk to you about live coding, developer joy, & how to easily build enterprise-grade AI apps using our native LangChain4j integration!
️
See you there!
@DevoxxUK #DevoxxUK #Quarkus #Java #AI #LangChain4j