The integration of large language models (LLMs) into structural engineering workflows presents both a transformative opportunity and a critical challenge. While LLMs enable intuitive, natural language interactions with complex data, their limited arithmetic reasoning, contextual fragility, and lack of verifiability constrain their application in safety-critical domains. This study introduces a novel automation pipeline that couples generative AI with finite element modelling through the Model Context Protocol (MCP)—a modular, context-aware architecture that complements language interpretation with structural computation. By interfacing GPT-4 with OpenSeesPy via MCP (JSON schemas, API interfaces, communication standards), the system allows engineers to specify and evaluate 3D frame structures using conversational prompts, while ensuring computational fidelity and code compliance. Across four case studies, the GPT+MCP framework demonstrated predictive accuracy for key structural parameters, with deviations under 1.5% compared to reference solutions produced using conventional finite element analysis workflows. In contrast, unconstrained LLM use produces deviations exceeding 400%. The architecture supports reproducibility, traceability, and rapid analysis cycles (6–12 s), enabling real-time feedback for both design and education. This work establishes a reproducible framework for trustworthy AI-assisted analysis in engineering, offering a scalable foundation for future developments in optimisation and regulatory automation.

This study addresses the challenge of optimizing flat-plate solar collector design, traditionally reliant on trial-and-error and simplified engineering design methods. We propose using physics-informed neural networks (PINNs) to predict optimal design conditions in a range of data that not only characterized the highlands of Ecuador but also similar geographical locations. The model integrates three interconnected neural networks to predict global collector efficiency by considering atmospheric, geometric, and physical variables, including overall loss coefficient, efficiency factors, outlet fluid temperature, and useful heat gain. The PINNs model surpasses traditional simplified thermodynamic equations employed in engineering design by effectively integrating thermodynamic principles with data-driven insights, offering more accurate modeling of nonlinear phenomena. This approach enhances the precision of solar collector performance predictions, making it particularly valuable for optimizing designs in Ecuador’s highlands and similar regions with unique climatic conditions. The ANN predicted a collector overall loss coefficient of 5.199 W/(m²·K), closely matching the thermodynamic model’s 5.189 W/(m²·K), with similar accuracy in collector useful energy gain (722.85 W) and global collector efficiency (33.68%). Although the PINNs model showed minor discrepancies in certain parameters, it outperformed traditional methods in capturing the complex, nonlinear behavior of the data set, especially in predicting outlet fluid temperature (55.05 °C vs. 67.22 °C).

This study evaluates the environmental impact of earthquake-resistant structural design choices in high-risk seismic regions through life cycle assessment. As climate change concerns intensify, understanding the environmental implications of structural design decisions becomes crucial for sustainable construction. Examining a building in Quito, Ecuador, the research compares three structural systems: Optimized Framed System (OFS), Optimized Dual System (ODS), and Equivalent Framed System (EFS). The assessment quantifies emissions through a ‘cradle to gate’ approach, encompassing materials fabrication, transportation, and construction processes. The results demonstrate that the ODS achieves optimal seismic performance equal to the EFS while reducing emissions by 38%, with only 5% higher emissions than the OFS. The findings establish that effective earthquake-resistant design can simultaneously achieve structural resilience and environmental sustainability, providing valuable insights for sustainable structural engineering practices in seismic regions.

The integration of large language models (LLMs) into structural engineering workflows presents both a transformative opportunity and a critical challenge. While LLMs enable intuitive, natural-language interactions with complex data, their limited arithmetic reasoning, contextual fragility, and lack of verifiability constrain their application in safety-critical domains. This study introduces a novel automation pipeline that couples generative AI with finite element modelling through the Model Context Protocol (MCP)—a modular, context-aware architecture that compliments language interpretation from structural computation. By interfacing GPT-4 with OpenSeesPy via MCP (JSON schemas, API interfaces, communication standards), the system allows engineers to specify and evaluate 3D frame structures using conversational prompts, while ensuring computational fidelity and code compliance. Across four case studies, the GPT+MCP framework demonstrated predictive accuracy for key structural parameters, with deviations under 1.5% compared to reference solutions produced using conventional finite element analysis workflows. In contrast, unconstrained LLM use produces deviations exceeding 400%. The architecture supports reproducibility, traceability, and rapid analysis cycles (6–12 seconds), enabling real-time feedback for both design and education. This work establishes a reproducible framework for trustworthy AI-assisted analysis in engineering, offering a scalable foundation for future developments in optimisation, and regulatory automation.

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.

The integration of Generative AI into civil engineering is currently constrained by the risk of non-compliant outputs and an inherent lack of physics-based knowledge. To address these limitations, this paper presents a conceptual framework for the integration of Agentic Artificial Intelligence (AI) into the complete lifecycle of seismic-resistant structural engineering. The proposal employs a modular software architecture built on the Model Context Protocol (MCP), enabling distributed collaboration among specialised AI agents. We operationalise this architecture across six critical stages, where specific agents govern distinct phases: (1) Seismic Hazard and (2) Structural Modelling agents quantify demands through deterministic tool execution; the (3) Design agent optimises element sizing under the strict governance of Retrieval-Augmented Generation (RAG) for code compliance; (4) Construction Quality Control and (5) Structural Health Monitoring (SHM) agents validate as-built geometry and service-life performance; and an overarching (6) Ethical Audit agent supervises the ecosystem to ensure safety and algorithmic transparency. By decoupling probabilistic design iteration from immutable numerical execution, this framework ensures that generative outputs are traceable, transparent, and professionally accountable, offering a verified pathway for the deployment of AI systems in structural engineering.