Build an MCP server with only the official Java SDK 2.1.0: tools and resources, a fat jar for Claude Desktop over stdio, Streamable HTTP on Jetty, and a Spring AI client connecting to it. Every output comes from a committed transcript.
A Spring AI streaming chat UI with no React: ChatClient to a Flux of server-sent events, an htmx front end, per-session memory, a Stop button that really cancels the model call, and back-pressure, all measured against a stub OpenAI-compatible server (no real provider was run).
Point one Spring AI 2.0.2 OpenAiChatModel at Docker Model Runner and at Ollama by changing only base-url and the model name. Same GGUF model, same prompts: decode speed, time to first token, container memory and tool-call success, with transcripts. Measured on a CPU-only shared sandbox with the real docker/model-runner image; GPU and Docker Desktop paths were not measured and the post says so.
A Spring Batch 6 chunk step calls a Spring AI ChatClient for 100,000 generated support tickets. Resilience4j rate limiting and retry, skip-and-record for malformed JSON, a restart after kill -9 in a second JVM that ends byte-identical, and a per-chunk cost ledger, all run against a deterministic simulated model with every number taken from a committed transcript.
20 copy-paste AI prompts for Java concurrency and CompletableFuture — from basics to advanced production patterns and debugging. Covers thread pools, ExecutorService, CompletableFuture chaining, fan-out/fan-in, timeout handling, virtual threads, deadlock diagnosis, thread dump analysis, and full concurrency audits.
A hands-on comparison of serverless Java AI inference on AWS Lambda, Azure Functions, and Google Cloud Run — with real benchmark data, cost tables, a clear winner recommendation, and code you can run.
A JEP-by-JEP deep dive into Java 25 LTS — the features that will actually change how you write and profile Java. Each section includes a before/after code example, an explanation of what the JVM does differently, the pitfall to avoid, and a copy-paste AI prompt to retrofit your existing codebase. Covers JEP 495, 494, 485, 492, 488, 491, 454, and JFR method profiling.
Python, TypeScript, and Java each claim dominance in the AI era — and they are all right, for different layers. This definitive guide maps which language owns the model layer, the orchestration layer, and the backend layer, with real code showing how all three work together in a complete AI system.
Traditional microservices, REST APIs, and relational databases were designed before AI became a first-class backend concern. This reference guide covers the five core principles of AI-native backend design — prompt-driven APIs, vector vs SQL decisions, event-driven pipelines, AI observability, and where current microservice patterns break.
Python rules AI research. Java rules enterprise production. In 2026, they're fighting for the same backend. This deep technical comparison — covering latency, memory, scalability, the GIL problem, and hybrid architecture patterns — settles where each language actually wins.