AI编程代理凭提示词生成软件架构，需建立审查机制。
Architecture Without Architects: How AI Coding Agents Shape Software Architecture
- 通过提示词特征映射到系统结构，形成隐式架构决策
- 相同任务因提示词不同生成差异显著的系统结构
- 提出六种提示-架构耦合模式，支持架构治理
AI编程代理可在数秒内选择框架、搭建基础设施并连接模块，这些均为架构决策，却几乎无人将其视为架构行为。本文识别出五种代理做出隐式架构选择的机制，并提出六种提示词与架构的耦合模式，将自然语言特征映射至所需基础设施。这些模式涵盖从依赖模型能力的条件性耦合（如结构化输出校验）到不受模型进步影响的根本性耦合（如工具调用编排）。演示表明，仅调整提示词即可生成结构不同的系统。该现象称为「氛围架构」——架构由提示词塑造而非刻意设计。论文提出审查流程、决策记录与工具支持，以实现对这些隐藏决策的治理。
原文摘要 · Abstract (English)
AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit architectural choices and propose six prompt-architecture coupling patterns that map natural-language prompt features to the infrastructure they require. The patterns range from contingent couplings (structured output validation) that may weaken as models improve to fundamental ones (tool-call orchestration) that persist regardless of model capability. An illustrative demonstration confirms that prompt wording alone produces structurally different systems for the same task. We term the phenomenon vibe architecting, architecture shaped by prompts rather than deliberate design, and outline review practices, decision records, and tooling to bring these hidden decisions under governance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。