This is an advanced course focused on designing and implementing Multi-LLM architectures and orchestration-centered Agent systems (Main/Sub, Tool, Task Runtime, Agent Registry) by strategically combining GPT, Gemini, and LLaMA (local) based on Spring AI and Spring Boot. Moving beyond simple LLM calls, the curriculum covers the implementation of scalable, stable, and continuously improving AI systems. This involves applying Agentic Workflow Patterns (Chain, Parallel, Routing, Orchestrator–Workers, Evaluator–Optimizer) and Multi-Agent structures, separating execution layers like RAG and external APIs/DBs via Tool/ToolRegistry, and utilizing DAG engines, YAML declarative workflows, and Validated DSL (validation immediately after loading). Furthermore, the course includes Circuit Breakers, Reactive Streams, Redis monitoring, parallel processing, and iterative evaluation loops. It expands from Thymeleaf (SSR) exercises to decoupled Front-end/Back-end architectures using React and REST, while integrating tool and agent runtimes via MCP (Model Context Protocol) to build AI architecture design capabilities at a production-ready level. The ultimate goal is to evolve beyond being a simple AI user who merely integrates APIs and writes prompts, becoming a developer capable of designing AI systems—explaining and balancing Multi-LLM, agents, workflows, declarations, and validation within a single execution architecture.

I highly recommend Spring AI to developers using Spring Boot and React, as well as those considering the introduction of AI systems in corporate environments. This course goes beyond a simple introduction to libraries; it helps you understand the core concepts and internal structure of Spring AI, and strengthens your practical implementation skills through various hands-on examples. The course is based on Spring AI version 1.1.x and provides continuous technical support and expansion strategies to ensure you can adapt to future version upgrades. Furthermore, we expand the practical value of Spring AI technology by utilizing MCP (Model Context Protocol) to achieve cross-domain context integration, AI linkage in distributed environments, and AI architecture design suitable for enterprise environments. With the goal of building AI systems that can actually be deployed in corporate settings, this will serve as a practical guide that balances theory and hands-on experience.