Automating Domain-Driven Design: Experience with a Prompting Framework

Dimensions overall score 4.0

• A prompting framework was developed to automate core Domain-Driven Design (DDD) activities using structured large language model (LLM) interactions.method 95%
  Evidencepartial

  This paper introduces a prompting framework that automates core DDD activities through structured large language model (LLM) interactions.

  Implicationpartial

  The abstract explicitly states the introduction of a prompting framework for automating DDD activities through LLM interactions.

  Verificationpartial

  partial

• The prompting framework decomposes DDD into five sequential steps: ubiquitous language, event storming simulation, bounded context identification, aggregate design, and technical architecture mapping.method 95%
  Evidencepartial

  We decompose DDD into five sequential steps: (1) establishing an ubiquitous language, (2) simulating event storming, (3) identifying bounded contexts, (4) designing aggregates, and (5) mapping to technical architecture.

  Implicationpartial

  The abstract clearly lists the five sequential steps that the DDD process is decomposed into by the framework.

  Verificationpartial

  partial

• The initial steps (1-3) of the prompting framework consistently generate valuable and usable artifacts for DDD.result 90%
  Evidencepartial

  While the first steps consistently generate valuable and usable artifacts, later steps show how minor errors or inaccuracies can propagate and accumulate.

  Implicationpartial

  The abstract and analysis excerpt both highlight the effectiveness of the early stages of the framework.

  Verificationpartial

  partial

• Later steps (4-5) of the prompting framework are affected by accumulated errors, rendering their generated artifacts impractical.result 90%
  Evidencepartial

  In our evaluation, Steps 1 to 3 worked well, but the accumulated errors rendered the artifacts generated from Steps 4 and 5 impractical.

  Implicationpartial

  The abstract and analysis excerpt explicitly mention the issues with later steps due to error propagation.

  Verificationpartial

  partial

• The prompting framework functions effectively as a collaborative sparring partner for generating documentation like glossaries and context maps, but not for full automation.limitation 95%
  Evidencepartial

  Overall, the framework excels as a collaborative sparring partner for building actionable documentation, such as glossaries and context maps, but not for full automation.

  Implicationpartial

  The abstract directly states the framework's utility as a sparring partner and its limitation for full automation.

  Verificationpartial

  partial

• LLMs can enhance architectural expertise in DDD but cannot replace it.technical 90%
  Evidencepartial

  Our findings show that LLMs can enhance, but not replace, architectural expertise, offering a practical tool to reduce the effort and overhead of DDD while preserving human-centric decision-making.

  Implicationpartial

  The conclusion of the abstract directly addresses the role of LLMs in relation to human expertise.

  Verificationpartial

  partial

• The prompting framework was validated against real-world requirements from FTAPI's enterprise platform in a case study.method 95%
  Evidencepartial

  In a case study, we validated the prompting framework against real-world requirements from FTAPI's enterprise platform.

  Implicationpartial

  The abstract explicitly mentions the case study used for validation.

  Verificationpartial

  partial

Competitive landscape

A prompting framework that automates core domain-driven design activities using LLMs to assist software architects.