This research introduces SENAI, a framework that bridges the gap between code-generating AI and core software engineering principles.

• Addresses current LLMs' inability to incorporate modularity, single responsibility, and concepts like cohesion and coupling
• Proposes a novel approach to evaluate and enhance AI code generation through software engineering fundamentals
• Uses Bloom's Taxonomy as an evaluation framework to assess comprehension levels
• Aims to create more maintainable, scalable, and robust software systems through AI assistance

This advancement matters because it potentially transforms AI coding assistants from mere code generators to software engineering partners that understand and apply engineering best practices.

SENAI: Towards Software Engineering Native Generative Artificial Intelligence