Paola Tapia

Modern engineering increasingly operates within socio-technical networks, such as the interdependence of energy grids, transport systems, and building codes, where decisions must be reliable and transparent. Large language models (LLMs) such as GPT promise efficiency by interpreting domain-specific queries and generating outputs, yet their predictive nature can introduce biases or fabricated values—risks that are unacceptable in structural engineering, where safety and compliance are paramount. This work presents a dataset that embeds generative AI into validated computational workflows through the Model Context Protocol (MCP). MCP enables API-based integration between ChatGPT (GPT-4o) and numerical solvers by converting natural-language prompts into structured solver commands. This creates context-aware exchanges—for example, transforming a query on seismic drift limits into an OpenSees analysis—whose results are benchmarked against manually generated ETABS models. This architecture ensures traceability, reproducibility, and alignment with seismic design standards. The dataset contains prompts, GPT outputs, solver-based analyses, and comparative error metrics for four reinforced concrete frame models designed under Ecuadorian (NEC-15) and U.S. (ASCE 7-22) codes. The end-to-end runtime for these scenarios, including LLM prompting, MCP orchestration, and solver execution, ranged between 6 and 12 s, demonstrating feasibility for design and verification workflows. Beyond providing records, the dataset establishes a reproducible methodology for integrating LLMs into engineering practice, with three goals: enabling independent verification, fostering collaboration across AI and civil engineering, and setting benchmarks for responsible AI use in high-stakes domains.

Modern engineering faces an unprecedented paradox: while our systems grow in-creasingly complex, the tools we use to design and evaluate them must remain both reliable and transparent. Decisions in energy, infrastructure, and construction no longer occur in isolation but within socio-technical networks shaped by emerging technologies and artificial intelligence (AI). Among these advances, large language models (LLMs) such as GPT have attracted attention for their ability to synthesize solutions, interpret domain-specific queries, and generate outputs with minimal fine-tuning. Yet beneath this promise lies a critical flaw—LLMs do not compute; they predict. Their reliance on sta-tistical associations often leads to biases, logical missteps, or hallucinated values, short-comings that become especially problematic when applied to structural engineering, where safety and compliance are non-negotiable. This tension sets the stage for the present work. The dataset introduced here responds to this gap by demonstrating how generative AI can be grounded within validated com-putational workflows. Through the Model Context Protocol (MCP), ChatGPT was con-nected to numerical solvers such as OpenSees and benchmarked against ETABS, ensuring traceability, reproducibility, and compliance with seismic design standards. The dataset comprises technical prompts, GPT outputs, verified numerical analyses, and comparative error metrics for four reinforced concrete frame models designed under Ecuadorian (NEC-15) and U.S. (ASCE 7-22) standards. Beyond a simple record, it exemplifies a re-producible methodology for embedding LLMs within structural engineering practice. By curating and releasing this dataset, the study pursues three goals: to strengthen re-producibility by enabling independent verification, to foster interdisciplinary collabo-ration across AI, civil engineering, and data science, and to establish benchmarks for context-aware AI integration in high-stakes domains. In doing so, it not only illustrates the promise of human–AI teaming but also highlights the limitations that must be addressed if generative models are to be responsibly embedded in engineering decision-making.

Background/Objectives: Miniscrew-Assisted Rapid Palatal Expansion (MARPE) has emerged as a widely adopted, non-surgical intervention for maxillary transverse deficiency (MTD) in adolescents and adults. Despite favourable clinical outcomes, treatment responses remain unpredictable due to anatomical variability and biomechanical complexities. This narrative review aims to evaluate the methodological robustness and translational potential of finite element method (FEM) models in simulating MARPE-induced craniofacial biomechanics. Methods: A structured literature search across five electronic databases, supplemented with AI-assisted screening tools, identified 70 relevant publications. Among these, 14 studies met the inclusion criteria for FEM-specific analysis, and 6 incorporated elements of clinical validation. The review critically assessed modelling practices, material assumptions, mesh characteristics, boundary conditions, and validation strategies. Results: FEM has proven effective in visualising stress distribution, displacement patterns, and mechanical thresholds in craniofacial structures during MARPE. However, significant methodological limitations were observed, including oversimplified geometries, lack of patient-specific imaging, reliance on isotropic and linear-elastic material assumptions, and insufficient clinical validation. These deficiencies reduce the predictive accuracy and clinical relevance of current FEM studies. Conclusions: To enhance the clinical applicability of FEM in MARPE research, future models should integrate anatomically accurate reconstructions, biologically informed boundary conditions, and longitudinal validation using CBCT data. Such advancements will enable evidence-based, patient-specific treatment planning and contribute to safer and more predictable orthodontic outcomes.

This study addresses the critical issue of indoor air quality (IAQ) and pathogen transmission within enclosed spaces at high altitudes, focusing on university classrooms in Quito, an Andean city in South America. The aim is to establish safety thresholds for room occupancy and permissible durations of exposure, tailored to this unique environmental context. Through an experimental approach conducted at an elevation of 2900 m above sea level, various natural ventilation strategies were evaluated for their efficacy in mitigating pathogen transmission risks. The study employs the Concentration Decay Test Method to characterize air changes per hour (ACH) and utilizes the Bazant mathematical model to predict occupancy levels based on ventilation, dimensions of the room, respiratory activity, infectiousness rates, and other parameters. Findings highlight the significant impact of ventilation strategies on room occupancy. Notably, higher infectiousness rates and large exposure times drastically reduce permissible occupancy levels, underscoring the importance of effective ventilation in maintaining safety. This research contributes valuable insights for informed decision‐making regarding classroom capacity and safety protocols in Andean higher education settings.