Home Events Building AI Systems with Spring AI

Building AI Systems with Spring AI

Description

Building AI Systems with Spring AI” is a comprehensive course that teaches developers how to design and implement production-ready AI-powered applications using the Spring AI framework. The course covers the full spectrum of modern AI development, from understanding core architectural concepts and prompt engineering to building conversational agents with memory, integrating retrieval-augmented generation (RAG) pipelines, leveraging tool calling and MCP, and deploying both cloud-based and offline language models.

 

🕒 Duration: 8 hours

👥 Target Audience:

  • Roles: Backend Engineers, Software Architects, Technical Leads, Solution Architects
  • Seniority: Mid- to senior-level professionals

Webinar Content
Module 1: Building AI Systems with Spring AI
Spring AI Core Concepts
  • AI vs traditional services
  • Spring AI architecture
  • ChatClient
  • Models/messages
  • System vs user instructions
Prompt Engineering
  • Prompt templates
  • Instruction vs context
  • Few-shot prompting
  • Structured outputs
Conversational AI & Memory
  • Stateless vs stateful conversations
  • Memory patterns (sliding window, summary, store-backed)
  • Memory lifecycle
RAG Foundations & Basic Monitoring
  • LLM hallucinations
  • RAG pipeline overview
  • query→retrieval→context→generation
  • Chunking strategies
  • Logging
  • Token usage monitoring
Tool Calling & MCP
  • Tools vs APIs
  • Validation
  • Error handling
  • Multi-step flows
  • MCP client/server basics
Offline & Hybrid LLM Deployment
  • Cloud vs offline models
  • Model selection & quantization
  • Docker deployment
  • Switching between cloud/local

 


Learning Objectives:

After attending this webinar participants will be able to:

  • Architect and build AI-powered services using Spring AI within a familiar Java/Spring ecosystem
  • Write effective prompts using templates, few-shot examples, and structured output techniques
  • Design stateful conversational applications with appropriate memory strategies
  • Implement RAG pipelines to ground LLM responses in real data and reduce hallucinations
  • Integrate external tools and MCP servers into multi-step AI workflows
  • Deploy and switch between cloud-hosted and locally running language models using Docker

Prerequisite Knowledge
  • Solid understanding of Java and the Spring Framework (Spring Boot experience is strongly recommended)
  • Familiarity with REST APIs and basic software architecture patterns
  • Basic understanding of what Large Language Models (LLMs) are and how they are used
  • Experience with Docker is helpful, particularly for the offline deployment module
Tags: