Single Conversation Methodology: A Human-Centered Protocol for AI-Assisted Software Development
This addresses the need for more structured and human-centered protocols in AI-assisted software development, though it appears incremental as it builds on existing LLM practices without introducing new technical methods.
The paper tackles the problem of ad hoc interactions with generative AI in software development by proposing the Single Conversation Methodology (SCM), a structured approach that uses a single, long-context conversation for all project stages, aiming to reassert the developer's active role as architect and supervisor.
We propose the Single Conversation Methodology (SCM), a novel and pragmatic approach to software development using large language models (LLMs). In contrast to ad hoc interactions with generative AI, SCM emphasizes a structured and persistent development dialogue, where all stages of a project - from requirements to architecture and implementation - unfold within a single, long-context conversation. The methodology is grounded on principles of cognitive clarity, traceability, modularity, and documentation. We define its phases, best practices, and philosophical stance, while arguing that SCM offers a necessary correction to the passive reliance on LLMs prevalent in current practices. We aim to reassert the active role of the developer as architect and supervisor of the intelligent tool.