Human–AI communication parameters for reproducible text-to-image workflows in AEC design across academia and practice

Generative artificial intelligence (AI) is increasingly incorporated into architecture, engineering, and construction (AEC) workflows, yet its adoption has advanced faster than the development of robust communication frameworks that ensure reproducibility, controllability, and methodological transparency. Academic research often emphasizes exploratory prototypes or technical advances, whereas professional practice depends on empirically tested input combinations that seldom follow systematic documentation. This review examines 190 academic publications (2000–2025) and 812 practitioner cases to identify the core human–AI communication variables structuring image-based generative workflows across platforms such as Midjourney, DALL-E, and Stable Diffusion. By synthesizing these variables into a cross-platform taxonomy, the paper reframes them as design levers and reproducible parameters for AEC design at an early stage. In doing so, the paper advances the goals of automation, standardization, and traceability in AEC workflows by demonstrating that reproducibility in generative design depends not only on model performance but on the communicability and documentation of user–model interactions.