From Context to Prompt: CSPM-Based Structured Prompting in AI-Assisted Spatial Design

Abstract This study proposes the Context Structures Perception Meaning (CSPM) as a structured prompt engineering methodology for generative AI-assisted design. CSPM is introduced as a structure-prompting approach that helps organize culturally embedded, multisensory design intentions into interpretable prompt structures. Rather than treating prompting in an unstructured manner, structured parameters help organize prompting structures for generative AI systems, addressing fundamental challenges in human-AI communication, including semantic drift, iterative dependency, and intention alignment. To clarify its operational validity, a comparative demonstration and a small practitioner reflection survey were conducted to compare unstructured prompting and CSPM-structured prompting using the same brief. The results suggest that unstructured prompts may produce visually sophisticated outputs and exhibit iterative stages with greater semantic drift and weaker traceability to encoded cultural values. The CSPM serves as a pre-prompting structure stage prior to AI execution. The prompting for CSPM-structured data reveals improved semantic consistency, reduced dependence on iteration, and clearer alignment with the intended meaning. CSPM reframes prompting as a human-centered AI by providing a systematic methodology for prompt engineering, interpretability, ambiguity reduction, and intention fidelity in generative workflows