<ul><li>Architectural Knowledge Management (AKM) is a challenge in software development due to the lack of standardization and manual effort involved.</li><li>Architecture Decision Records (ADRs) offer a structured approach to capture Architecture Design Decisions (ADDs), but their adoption is limited due to manual effort and insufficient tool support.</li><li>Research has explored using Large Language Models (LLMs) to generate ADDs, but there is a need to enhance the quality of generated ADDs.</li><li>The proposed approach, called DRAFT, combines few-shot, retrieval-augmented generation (RAG) and fine-tuning techniques to generate more effective ADDs while addressing privacy and resource challenges.</li></ul>

DRAFT-ing Architectural Design Decisions using LLMs

Discover more