Expertise & Sharing
As an IT consultant, author and tech entrepreneur, I support organizations in designing, modernizing and evolving their software systems, as well as integrating generative AI into business activities and software delivery. I also share my experience through articles, training, conferences and active involvement in technical communities.
My expertise lies at the intersection of software engineering, systems architecture, fullstack development, applied artificial intelligence, and technical sharing.
Design of robust applications, modular architectures, APIs, Java backend, Spring, Quarkus, hexagonal architecture, microservices and enterprise systems.
Integration of LLMs, RAG, AI agents, Spring AI and conversational systems into concrete business applications.
Web, mobile and backend application development with an approach oriented towards quality, maintainability, performance and business value.
Articles, conferences, training and educational content around software engineering and applied AI.
My path has been built between corporate missions, open source contributions, technical training and entrepreneurial projects. I intervene as an IT consultant, software architect, fullstack developer, trainer, speaker and founder of Gad Digital.
Learn more about my backgroundSupporting companies in various sectors: financial services, fintech, games, education, public services, industry and health.
Active participation in Java and AI projects (Spring AI) and publication of libraries like Toon4j.
Mentoring developers and introducing young people to robotics, home automation and embedded systems.
Published by Orange AVA, this book is dedicated to Java design patterns, modern software architecture and the design of robust, maintainable and scalable applications.
View the book
Gad Digital is the technology company I founded to transform my expertise into concrete solutions, products and support. Through Gad Digital, I lead initiatives around digital solution development, applied AI and technical training.
Discover Gad DigitalBlog
Comparing Two Versions of an LLM System
Identify and qualify behavioral changes in an LLM system when the model, the prompt, the tools, or the rules evolve, to tell an improvement apart from a regression.
Building a Representative Evaluation Set
Build an evaluation corpus that represents an LLM system's usages, edge cases, and invariants, to give version comparisons a solid foundation.
Detecting and Qualifying Behavioral Drift
Tell an acceptable behavioral drift apart from a real regression in an LLM system, by qualifying it through nature, frequency, scope, and impact rather than a single overall score.
YouTube
Gallery
Click on bubbles to view images fullscreen
Get my notes on Java, AI, and software engineering delivered straight to your inbox.
No spam. Unsubscribe anytime.
