Purpose This paper aims to propose and validate a framework for conversational AI assistance in BIM-based MEP coordination through a proof-of-concept prototype integrating MCP with Autodesk Navisworks, addressing the post-detection decision support gap. Design/methodology/approach A Design Science Research approach guided development and validation of the framework as the primary artifact, instantiated as an MCP-Navisworks prototype and evaluated through three tests on a real residential building project to identify conditions of use rather than generalizable performance. Findings The framework demonstrated technical viability across all tests. Intelligent grouping produced 20 prioritized element groups from 45 unique clashes, though four clashes were assigned to two groups simultaneously. Across the three resolution cases, the assistant surfaced the coordinator’s adopted solution among its suggested alternatives, though alongside non-adopted options and, for the most complex clash, only after explicit dimensional data was supplied. Research limitations/implications Findings establish technical viability rather than generalizable performance. Performance is constrained by input data quality and current LLM spatial reasoning capabilities. No timing or efficiency measurements were collected. Practical implications Natural-language interaction offers a potential route to supporting post-detection clash analysis. Originality/value Building on an open-source MCP-Navisworks base limited to basic model communication, the study’s specific technical contribution is a Clash Detective integration enabling a conversational AI to read and analyze native clash results, through a three-layer architecture validated as an exploratory proof of concept documenting where LLM-based assistance helps and where it fails.
Purpose The engagement of technology users, providers and investors plays a vital role in shaping innovation pathways within the construction industry. As digital platforms increasingly host professional discussions on emerging technologies, analyzing these narratives is essential for understanding how adoption and investment trends develop. This paper aims to examine how discourse in the construction technology (ConTech) ecosystem reflects funding trends and how firms strategically position themselves. Design/methodology/approach This study adopts an exploratory, abductive mixed-methods approach combining BERTopic-based topic modelling, network analysis and qualitative synthesis. Automated topic detection is complemented by author refinement to identify key themes and priorities in professional digital conversations. Data was collected through purposive sampling from eight construction technology platforms, including institutional websites and LinkedIn blogs authored by verified ConTech professionals. The analysis was conducted in Python using BERTopic and network analysis tools. Findings Knowledge spillovers cluster around 13 coherent topics, with “Venture Capital Strategies and Trends” emerging as the most prominent, underscoring the central role of investment discourse in shaping innovation trajectories. Network analysis confirms this focus, identifying “venture capital” as the most influential connective term across themes. Other key topics include “Robotic Solutions in Construction” and “AEC Digital Innovation and Technology Adoption.” The findings of this study reveal opportunities and persistent barriers to adoption related to integration, compatibility and risk, while emphasizing the importance of collaboration, role clarity and viable business models. Originality/value This study reveals how funding-related discourse coordinates digital transformation in construction by shaping legitimacy, strategic priorities and technology adoption. By mapping discursive centrality and thematic brokerage, it uncovers emerging innovation directions that conventional taxonomies overlook, offering actionable insights for firms, investors and technology startups.
Purpose To effectively support the housing sector, the offsite construction (OSC) supply chain (SC) requires strengthened skills, expanded operational capacity and improved organisational capabilities. However, ongoing SC management (SCM) issues, such as cost overruns, inefficient processes and material waste, continue to limit the housing sector’s adoption of OSC. By addressing these barriers, this study aims to improve OSC-SCM processes while expanding the talent and capability base needed for construction ecosystems. Design/methodology/approach A system dynamics (SD) modelling approach is used to analyse cost and time dynamics under multiple disruption scenarios quantitatively. The model incorporates key barriers, like design inefficiencies, labour shortages, equipment delays and logistical constraints, while also simulating the potential performance gains achievable through skill development, capacity expansion and capability upgrading. Findings The simulation results demonstrate the complex relationships among SC performance, operational capacity and personnel capability in OSC. The findings point to key areas for leverage where focused interventions, such as digital design integration, improved worker training and rapid logistics planning, can increase productivity, cut waste and improve preparedness simultaneously. Originality/value In the OSC context, this research presents a novel integration of SD modelling, showing how digitally driven skill enhancement and capacity building can serve as catalysts for attaining next-generation construction performance and overcoming enduring SCM barriers.
Purpose This research aims to propose and validate a methodology for customizing generative artificial intelligence (GenAI) to enhance its performance in a specialized domain in construction, using Finnish hospital construction as a case study. Design/methodology/approach Using a design science methodology, the study follows a three-step process: (1) problem and requirement framing, (2) solution development and (3) validation. The study applies specific research methods for GenAI customization to operationalize this framework, including domain-specific dataset curation, retrieval-augmented generation and iterative, expert-in-the-loop, qualitative validation. Findings The study indicates that a cost-effective GenAI customization can provide more relevant and useful responses than standard models in domain-specific use with approximately 120 work hours invested in customization. The validated methodology provides a transferable framework that encompasses four key stages: (1) problem and requirement framing; (2) domain-specific dataset creation, curation and sanitization; (3) model constitution and retrieval-augmented configuration; and (4) expert validation and refinement. The most resource-intensive stages were creating and curating the dataset and recruiting experts for validation. Originality/value This study offers an original contribution by demonstrating customizing GenAI for the specific localized context in construction. It underscores the importance of curated data sets and provides a validated pathway for continuous data-driven improvement.
Purpose Existing reviews on modular construction are largely dominated by building- or system-level perspectives, while the limited component-level reviews remain mainly connection-focused. This leaves a limited understanding of what modular building components have been studied, what design methods are used at the component level and what key challenges shape future research. This study aims to address these gaps through a systematic literature review of modular building component design. Design/methodology/approach A systematic literature review was conducted following PRISMA guidelines. Scopus and Web of Science were used as the primary databases, and 75 peer-reviewed journal articles published between 2010 and 2024 were selected after screening and eligibility assessment. Template analysis was applied to synthesise evidence on component types, design methods and approaches, and reported challenges and future directions. Findings The review identifies nine component types and organises design methods into three functional roles: design generation, design strategy and decision-making, and design verification and improvement. It also highlights four recurring challenges: uneven component coverage, limited transferability of verification evidence, weak upstream integration of life cycle constraints and the limited integration of AI and digital methods with validated evidence. Originality/value This review provides a component-centred and workflow-oriented synthesis of modular building component design, extending prior building-level and connection-focused reviews. By integrating component types, material categories and design methods within one analytical framework, it clarifies how current knowledge is distributed across generation, decision strategy and verification. It also informs implications for design practice, industry implementation, education and policy, supporting more reusable, life cycle-informed and performance-grounded design workflows.
