Leveraging Generative AI for Enhancing Domain-Driven Software Design

2026-01-28

AI Summary

This work proposes a novel generative AI–based approach to automate domain-driven design (DDD) by generating syntactically correct and semantically accurate domain-specific JSON metamodels, addressing the inefficiency and high cost of manual metamodel construction in traditional DDD. By integrating 4-bit quantized Code Llama with LoRA fine-tuning, the method enables efficient inference on consumer-grade GPUs. With only minimal prompting, the model produces outputs that require little to no post-processing, substantially reducing computational resource demands. Experimental results demonstrate that this approach significantly enhances DDD modeling efficiency under constrained hardware conditions, thereby validating the feasibility and practical utility of generative AI in domain modeling tasks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Domain-Driven Design
• metamodel generation
• generative AI
• JSON objects
• software design automation

Innovation

• Generative AI
• Domain-Driven Design
• Metamodel Generation
• Low-Rank Adaptation
• 4-bit Quantization