Beyond Greenfield: The D3 Framework for AI-Driven Productivity in Brownfield Engineering

TL;DR

This paper introduces the D3 Framework, a structured LLM-assisted workflow designed to improve productivity and clarity in brownfield engineering tasks involving legacy systems, with promising preliminary practitioner-reported results.

Contribution

The paper presents the novel D3 Framework, combining role-separated prompting and dual-agent architecture to address challenges in complex, legacy engineering environments.

Findings

Reported 26.9% productivity improvement

77% experienced reduced cognitive load

83% spent less time fixing code

Abstract

Brownfield engineering work involving legacy systems, incomplete documentation, and fragmented architectural knowledge poses unique challenges for the effective use of large language models (LLMs). Prior research has largely focused on greenfield or synthetic tasks, leaving a gap in structured workflows for complex, context-heavy environments. This paper introduces the Discover-Define-Deliver (D3) Framework, a disciplined LLM-assisted workflow that combines role-separated prompting strategies with applied best practices for navigating ambiguity in brownfield systems. The framework incorporates a dual-agent prompting architecture in which a Builder model generates candidate outputs and a Reviewer model provides structured critique to improve reliability. I conducted an exploratory survey study with 52 software practitioners who applied the D3 workflow to real-world engineering tasks such as legacy system exploration, documentation reconstruction, and architectural refactoring. Respondents reported perceived improvements in task clarity, documentation quality, and cognitive load, along with self-estimated productivity gains. In this exploratory study, participants reported a weighted average productivity improvement of 26.9%, reduced cognitive load for approximately 77% of participants, and 83% of participants spent less time fixing or rewriting code due to better initial planning with AI. As these findings are self-reported and not derived from controlled experiments, they should be interpreted as preliminary evidence of practitioner sentiment rather than causal effects. The results highlight both the potential and limitations of structured LLM workflows for legacy engineering systems and motivate future controlled evaluations.