Risk management in large-scale construction projects is a critical yet complex process influenced by financial, safety, environmental, scheduling, and regulatory uncertainties. Effective risk management contributes directly to project optimization by minimizing disruptions, controlling costs, and enhancing decision-making efficiency. Early identification and mitigation of risks allow resources to be allocated where they have the greatest effect, thereby optimizing overall project outcomes. However, conventional methods such as expert judgment and probabilistic modeling often struggle to process extensive datasets and complex interdependencies among risk factors. This study explores the potential of an AI-based framework for risk identification, utilizing artificial intelligence to analyze project documentation and generate a preliminary set of identified risks. The proposed methodology is implemented on the ‘Trg pravde’ judicial infrastructure project in Zagreb, Croatia, applying AI models (GPT-5, Gemini 2.5, Sonnet 4.5) to identify phase-specific risks throughout the project lifecycle. The approach aims to improve the efficiency of risk identification, reduce human bias, and align with established project management methodologies such as PM². Initial findings suggest that the use of AI may broaden the range of identified risks and support more structured risk analysis, indicating its potential value as a complementary tool in risk management processes. However, human expertise remains crucial for prioritization, contextual interpretation, and mitigation. The study demonstrates that AI augments, rather than replaces, traditional risk management practices, enabling more proactive and data-driven decision-making in construction projects.

This paper represents initial research with the aim to establishes a baseline for subsequent research into AI-based construction monitoring, building upon the NORMENG project in Croatia, which previously integrated photogrammetry, laser scanning, and BIM-based methods. The study tests general purpose AI’s ability to detect materials and estimate quantities, aiming to assess whether a broad, context-aware AI system can match the precision of specialized, domain-specific tools or even human work needed for productivity estimations. While the AI demonstrated potential for basic entity detection and preliminary quantity estimations, it showed significant limitations in delivering fine-grained, temporally accurate breakdowns without targeted adaptation. The findings underscore the need for domain-specific fine-tuning and human-in-the-loop validation to transform AI into a reliable tool for construction management. This initial contribution provides empirical insights and actionable recommendations for advancing automated progress monitoring in the construction sector.

While Digital Twins offer transformative potential, their efficacy for real-time control is constrained by the slow data acquisition and the high computational intensity required to process raw datasets like point clouds. This paper identifies these critical bottlenecks—specifically the latency between data capture and actionable insight—and proposes a refined theoretical framework for near-real-time automated progress monitoring and quality reporting. Building on the findings of the NORMENG project and informing the subsequent AutoGreenTraC project, this research synthesizes state-of-the-art advancements in reality capture, including LIDAR, SfM-MVS, and 360-degree vision. The study highlights a fundamental divergence in stakeholder requirements: the need for millimeter-level precision in quality control versus the demand for high-velocity documentation for progress monitoring. A key innovation presented is the shift toward neural rendering techniques to bypass the computational delays of traditional photogrammetry and enable immediate on-site visualization. By structuring a tiered processing hierarchy that combines lightweight edge analysis for immediate safety and progress monitoring with asynchronous high-fidelity Digital Twin updates, the framework aims to establish a single source of truth.

The technological process map, a construction-specific form of the ASME flow process chart, records the works of a construction site in their technological sequence together with the transports, inspections, delays and storages that schedules omit. Although valued in teaching, it is rarely drawn in practice because it is slow to produce. This paper examines whether a general-purpose large language model can generate the map from tender documents that describe the product and its requirements rather than the construction process as a sequence, and whether the project documentation, the bill of quantities or both is the input that determines the result. For ten road construction tenders of one public client, the same model generated a map three times, zero-shot, from each of these three inputs. An independent LLM agent matched the ninety maps step by step, and the differences between inputs were judged against the variation between repeated generations from the same input. Maps built from the bill of quantities were about 40% larger than maps built from the documentation alone, while adding the documentation to the bill changed the map only slightly more than two repeated generations from the same input differed. All measures are structural and do not assess correctness, which is the subject of the expert validation that follows. The results identify the bill of quantities as the input to start from and provide the material for that validation.