Leveraging Generative AI for Enhancing Domain-Driven Software Design

TL;DR

This paper demonstrates that generative AI can partially automate the creation of domain-specific metamodels in Domain-Driven Design, reducing manual effort and resource requirements while maintaining accuracy.

Contribution

It introduces a method for fine-tuning generative AI models on real-world DDD data to produce syntactically correct JSON objects from simple prompts.

Findings

AI-generated JSON objects are syntactically correct and accurate.

Fine-tuning with low-resource hardware is effective.

The approach streamlines the DDD design process.

Abstract

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.