Blog
I write about Java, software architecture, design patterns, applied artificial intelligence, RAG, AI agents and software engineering. Through my articles, I share feedback, technical analyzes and concrete approaches to design robust, maintainable and useful applications.
RAG in practice: Industrializing unstructured data for AI use cases
Corpus quality, security, governance, indexing, and evaluation: The foundations needed to move from AI POCs to reliable and sustainable use cases.
RAG in Practice : From Retrieval to Business Reasoning
Once the data layer is in place, the real challenge is turning a RAG system that retrieves passages into one that produces structured, useful, and justifiable business answers.
RAG in Practice: Why Everything Starts with Data Engineering
In a real RAG project, answer quality often depends less on the model than on how documents are collected, cleaned, structured, and split. A field perspective based on a project built on a complex business corpus.
Model Context Protocol (MCP) with Spring AI: Exposing and Consuming Remote Tools
The Model Context Protocol (MCP) is an open protocol that standardizes communication between AI applications and external tools. In this article, we build an MCP Server that exposes a RAG tool and an MCP Host that orchestrates it alongside the GitHub MCP server.
Multi-Agent Orchestration with Spring AI
What if instead of a single AI agent, you orchestrated several in parallel? In this article, we build a multi-agent workflow with Spring AI: specialized agents execute in parallel via Java Virtual Threads, then an evaluator qualifies the overall result.
Securing AI Tools with Spring Security
When an LLM can call your Java methods, security becomes critical. In this article, we combine Spring AI and Spring Security to control access to AI tools with @PreAuthorize and HTTP Basic authentication.
Function Calling with Spring AI: When the LLM Calls Your Java Methods
Function Calling allows the LLM to call server-side functions to access real-time data. Spring AI offers two approaches: functions declared as Spring beans (@Bean + @Description) and methods annotated with @Tool. Let's discover both patterns.
