starting point: 

How can design data (BIM, CAD, etc.) be used to support data-intensive scenario planning (predictive modelling) for the Architecture, Engineering, and Construction Sector? What methods are available for using predictive modelling to help architects during the design process? 

This topic may include consideration of: cognitive, cultural, and social factors when using data in the design process. 

project summary: 

As a result of rapid technological advancement due to ‘industry 4.0’, digitalisation is one of the core drivers influencing the development of the Architecture, Engineering, and Construction (AEC) sector (Zawada et al., 2024). However, the AEC industry sector remains one of the slowest adopters of digital technology globally (Li et al., 2025). In this context, AI is seen as possible solution, yet its adoption in the sector is generally fragmented and isolated from traditional workflows, limiting its effectiveness (Zhang et al., 2022). The complexity of architectural design also demands more standardised and comprehensive integration strategies. Otherwise, AI use may even increase time and costs or reduce cognitive engagement (Becker et al., 2025, Kosmyna et al., 2025). In parallel, creativity is also a critical factor in the architectural profession (Parente et al., 2023), and isolated GenAI tools are less capable of supporting innovation (Tan and and Luhrs, 2024).  

This research seeks to bridge the gap between functional creativity (Hassan, 2018) and Human AI collaboration (HAIC), aiming to support the AEC sector in enhancing innovation within a highly competitive market. 

To achieve this aim, it is essential to understand how AI can be employed in the architectural workflow with a balanced in human cognition and efficiency through a strategy. Additionally, transforming AI from a tool into a collaborator, that can augment each other’s complementary strengths (Dellermann et al., 2019), could resolve the problems of isolated and discontinuous AI integration.  

research gaps | aims:  

Three gaps of knowledge identified in the past research: 

1. Creative Collaborator: The role of AI in AEC field is still limited to external automatic tools, with few studies concern it as a design collaborator. This may ignore the strength of communication ability, especially from the large language models.  

2. Functional Creativity: Assessments of creativity often prioritises novelty over or ignore functional performance. This may lead to impractical design for real-world applications.  

3. Integrating AI: AI integration into standard design workflows is fragmented, lacking unified workflow, strategies, and guidelines for effective adoption. 

This research has two aims: 

1. to test whether human-Artificial Intelligence (AI) collaboration (HAIC) in early-stage architectural design can enhance functional creativity  

2. to identify the factors that support or hinder HAIC in architectural design. 

 The study involves three phases: 

• Comprehensive Systematic Literature Review 

• Controlled Experiment 

• Data analysis: Protocol Analysis & Lab streaming layer analysis 

For monitoring the creativity engagement, this research introduces a Lab Streaming Layer approach to connect designers’ behaviours and their brain signal activities together with electroencephalogram (EEG) devices. With this information, this research will build a model that can estimate and predict the most effective point where designers work best in collaboration with AI. 

contribution to industry: 

This research may contribute to the AEC industry by developing a standard guideline that meets the needs of industry partners in integrating AI into their current workflow (reduce risk, increase innovation & creativity). In doing so, it provides practical strategies for seamless collaboration between designers and LLM AI, helping AEC sectors deliver more creative, sustainable, and client-oriented design solutions.  

references: 

BECKER, J., RUSH, N., BARNES, E. & REIN, D. 2025. Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity. Available: https://ui.adsabs.harvard.edu/abs/2025arXiv250709089B [Accessed July 01, 2025]. 

DELLERMANN, D., EBEL, P., SÖLLNER, M. & JAN MARCO, L. 2019. Hybrid Intelligence. Business & Information Systems Engineering, 61, 637-643. 

HASSAN, D. K. 2018. Divergent thinking techniques discrepancy and functional creativity: Comparative study of structural and procedural techniques in architectural design. Ain Shams Engineering Journal, 9, 1465-1479. 

KOSMYNA, N., HAUPTMANN, E., YUAN, Y. T., SITU, J., LIAO, X.-H., BERESNITZKY, A. V., BRAUNSTEIN, I. & MAES, P. 2025. Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task. arXiv preprint arXiv:2506.08872. 

LI, H., ZHANG, Y., CAO, Y., ZHAO, J. & ZHAO, Z. 2025. Applications of artificial intelligence in the AEC industry: a review and future outlook. Journal of Asian Architecture and Building Engineering, 24, 1672-1688. 

PARENTE, J., RODRIGUES, E., RANGEL, B. & POÇAS MARTINS, J. 2023. Integration of convolutional and adversarial networks into building design: A review. Journal of Building Engineering, 76, 107155. 

TAN, L. & AND LUHRS, M. 2024. Using Generative AI Midjourney to enhance divergent and convergent thinking in an architect’s creative design process. The Design Journal, 27, 677-699. 

ZAWADA, K., RYBAK-NIEDZIÓŁKA, K., DONDEREWICZ, M. & STARZYK, A. 2024. Digitization of AEC Industries Based on BIM and 4.0 Technologies. Buildings, 14, 1350. 

ZHANG, F., CHAN, A. P. C., DARKO, A., CHEN, Z. & LI, D. 2022. Integrated applications of building information modeling and artificial intelligence techniques in the AEC/FM industry. Automation in Construction, 139, 104289.