Leveraging Generative AI for Enhancing Domain-Driven Software Design
This work addresses the efficiency and resource challenges in software design for developers, though it is incremental as it builds on existing AI methods for a specific domain.
This paper tackles the manual creation of metamodels in Domain-Driven Design by partially automating it with generative AI, demonstrating that a fine-tuned model can generate syntactically correct JSON objects from simple prompts, achieving high performance with minimal post-processing on limited hardware.
Domain-Driven Design (DDD) is a key framework for developing customer-oriented software, focusing on the precise modeling of an application's domain. Traditionally, metamodels that describe these domains are created manually by system designers, forming the basis for iterative software development. This paper explores the partial automation of metamodel generation using generative AI, particularly for producing domain-specific JSON objects. By training a model on real-world DDD project data, we demonstrate that generative AI can produce syntactically correct JSON objects based on simple prompts, offering significant potential for streamlining the design process. To address resource constraints, the AI model was fine-tuned on a consumer-grade GPU using a 4-bit quantized version of Code Llama and Low-Rank Adaptation (LoRA). Despite limited hardware, the model achieved high performance, generating accurate JSON objects with minimal post-processing. This research illustrates the viability of incorporating generative AI into the DDD process, improving efficiency and reducing resource requirements, while also laying the groundwork for further advancements in AI-driven software development.