Architecture Without Architects: How AI Coding Agents Shape Software Architecture

TL;DR

AI coding agents rapidly make architectural decisions in software development, often without explicit review, leading to a phenomenon called vibe architecting where prompts shape system structure.

Contribution

The paper identifies mechanisms and patterns of implicit architectural decisions made by AI agents and introduces practices to govern these hidden choices.

Findings

Prompt wording significantly affects system structure.

Six prompt-architecture coupling patterns are proposed.

Vibe architecting influences software architecture without deliberate design.

Abstract

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.