
< session />
Wed, April 22BackEndDeepTech Architecture
This session demonstrates a practical approach to building applications by starting with a system use case and using AI to generate a full-stack Java application. The workflow focuses on evolving features by modifying the specification and observing how the code adapts in real time. It highlights how keeping specifications, code, and tests aligned can improve reliability and reduce inconsistencies.
Through a live, collaborative session, you will see how strong guardrails help reduce hallucinations and maintain consistency between requirements and implementation. The approach is tool-agnostic and can be applied with different AI agents, allowing comparison of outcomes across tools.
What You Will Learn
How to generate and evolve a full-stack Java application from a use case using AI
How to keep specifications, code, and tests in sync during iterative development
How to use guardrails to reduce hallucinations and improve consistency in AI-generated code
Who Should Attend
Java developers
Software engineers exploring AI-assisted development
Software architects
Engineering teams evaluating spec-driven workflows with AI
< speaker_info />
Simon Martinelli is a Java Champion, Vaadin Champion, and Oracle ACE Pro, with over three decades of experience as a software architect, developer, consultant, and trainer.
As the owner of Martinelli LLC, he specializes in optimizing full-stack development with Java and has a deep focus on modern architectures and software modernization.
He frequently shares his expertise by speaking at international conferences, writing articles, and maintaining his blog, Keep It Simple: https://martinelli.ch.
His passion for teaching is reflected in his work as a lecturer at two universities of applied sciences in Switzerland.