This paper presents an iterative approach for geometric constructions with a compass and straightedge. It is based on Forward and Backward Reaching Inverse Kinematics (FABRIK) developed by Andreas Aristidou and Joan Lasenby. FABRIK is a fast and reliable kinematic solution mostly used in fields such as character animation and robot programming. In this study, we attempt to translate the FABRIK solution into a compass-and-straightedge construction, aiming to reveal new interdisciplinary research topics. After a brief historical and theoretical background, the methodology of FABRIK is explained with the notation of Geometrography. A Python tool was developed to run within the computer-aided design software Rhinoceros. Finally, this tool was used to test the proposed algorithm. The test approximates the construction of a regular heptagon, which is impossible to construct with a compass and straightedge. From architectural robotics to architectural geometry and education, this topic spans scales and joins disciplines. This paper aimed to establish a conceptual bridge between distinct fields of applied geometry, based on their mathematical foundations. The synthetic solutions of computational geometry and robotics can merge with the research path of Geometrography by translating their results into abstract compass-and-straightedge constructions. There are several future research topics in this field. One of them is the research and education of architectural robotics. Moreover, the folding of the regular heptagon can be further extended.

In the context of the continual evolution of advanced architectural design tools, driven by computational and artificial intelligence technologies, the practice of design can now benefit from contextually-driven and iterative design workflows. Thus, computational and AI tools have huge potential to enhance the conceptual design processes in architecture, due to their advanced workflow qualities. Node-based interfaces of these tools serve as a catalyst, enabling workflows that are adaptable to different requirements and needs of the design processes. This paper explores juxtaposing node-based computational design and AI tools in a dependent workflow process using Grasshopper3D and ComfyUI, within the framework of an experimental architectural concept development process, through a qualitative Research-through-Design methodology (RtD). Through a series of controlled experiments, multiple architectural design schemes are generated and categorized into four distinct visual identities: blob, biophilic, vernacular, and modern. These categories serve as a comparative framework to evaluate the adaptability and responsiveness of the integrated workflow across different design intentions. The process emphasizes iteration and variation, but with contextual responsiveness, testing a more streamlined refinement process of design schemes. The findings demonstrate that integrating node-based computational scripting with AI-driven workflows enhances the capacity for rapid iteration, supports the generation of diverse and contextually relevant architectural concepts, and enables more fluid transitions between abstract and representational stages of design. This research contributes to the advancement of architectural design methodologies by implementing a hybrid workflow model that bridges computational logic and generative AI capabilities, showcasing new potentials for concept development in contemporary architectural practice.

Generative AI tools such as ChatGPT and Claude are reshaping design practice, and AI now takes part in the early phases of the design process, including idea generation, concept development and decision-making. Because the quality of an AI-generated output depends on how the designer communicates with the model, prompt design has become the primary communication channel between designer and AI. Existing prompt engineering scholarship examines how the structure of a prompt affects model performance — through chain-of-thought reasoning steps or zero-shot reasoning triggers; the question of how far the theoretical intent behind a prompt survives into a visual design output has received little systematic attention. This exploratory study examines six prompting strategies through a fictional task management application, TaskFlow. Each strategy rests on a distinct theoretical foundation: Basic Prompt (zero-shot prompting), Design Brief (chain-of-thought), Simplification Focus (cognitive load theory), Inspiration Based (abductive thinking), Problem Focused (human-centred design) and Emotion/Tone Based (emotional design). For each strategy Claude Opus 4.5 produced a written design definition, which was converted into a functional prototype interface through Figma Make AI (Default). Five professional UI/UX designers evaluated the seven outputs (one reference interface and six strategy outputs) in a single blind focus group session, using applicability, user-centredness and inspirational quality as criteria. None of the outputs was adopted as a whole by any participant. The two strategies whose theoretical intent became most directly visible in the output, Emotion/Tone Based and Problem Focused, attracted the most positive assessments across all three criteria, expressing their intent through concrete visual counterparts. By contrast, the Design Brief strategy, which supplied the most extensive context, did not control the direction of the output, which drifted from task management towards habit tracking; within this dataset the amount of information supplied does not appear to guarantee the realisation of intent. As the intent of a prompt narrowed, the user base addressed by the output tended to narrow with it, although the Emotion/Tone Based strategy stood outside this tendency, possibly because its emotional design framework does not depend on a specific persona. None of the five participants framed AI as a co-designer or creative partner; all positioned it as a tool operating under the designer’s judgement, which sits in tension with a literature that often casts AI as an active actor. Intent-output alignment was not a framework tested in advance but a pattern that emerged during the analysis of the focus group data; the study proposes it, across the three dimensions of presence, direction and boundary, as an analytical axis that warrants examination in further research. Given the single session, the five participants and the single output generated per strategy, the findings should be read as context-specific and exploratory rather than generalisable.

Modern urban rail transport infrastructure projects are designed with the help of architectural designs that integrate different modes of transport and regulate multi-directional passenger flows, transfers, and passenger platform guidance mechanisms, etc. Railway system station areas have become increasingly complex spaces with diversified functionalities due to increasing passenger volumes. Quality, comfort, and performance-oriented transportation infrastructure designs significantly complicate the empirical study of crowd distribution models; this challenge is even more pronounced in structures where historical heritage must be preserved. Marmaray Sirkeci Railway Station area hosts a heterogeneous pedestrian profile due to its museums, waiting areas, tourist attractions, and its role as an integration point with high-density passenger circulation enabling intercontinental transit. To analyze these complex pedestrian dynamics, an object-oriented, agent-based cellular automata pedestrian simulation engine was developed in Python to investigate different travel behaviors. Pedestrian behavior patterns such as walking, waiting, queuing, and accumulating are spatially encoded in a layout plan using a 40 x 25 matrix structure, where each cell represents a spatial constraint. Multi-agent physical interactions, pedestrian accumulation changes, and spatial boundaries were modeled using the Manhattan Distance Function combined with directional floor areas and collision avoidance algorithms. Key findings from the simulation outputs, spatial density heat maps were used to evaluate critical operational transitions at ticket offices, main hall passages, and Marmaray entrance corridors. Consequently, the model outputs produced in this study allow for the proposal of feasible, long-term operational circulation arrangements, optimized ticketing layouts, and adaptable flow management strategies designed to maximize passenger comfort, reduce queue formation, and improve emergency evacuation safety while preserving the historical architectural integrity of the station for transportation infrastructure design and renovation phases.

The construction industry is multidisciplinary. It requires strong collaboration and seamless data exchange between all engaged stakeholders across various project phases, including design, construction, and operation. Within these phases, quality and compliance control is essential. It ensures that the project meets requirements and helps identify errors or missing information. However, traditional model control processes, which rely on manual methods conducted by people, are often error-prone and time-consuming. To address these challenges, adopting automated workflows for compliance checking have become crucial to improve overall efficiency and minimize errors in construction projects. Aligned with this objective, Building Information Modeling (BIM) has emerged as an effective methodology for data exchange and collaboration. Despite its advantages, the information contained in BIM models can be challenging to manage and is often overlooked for updates, especially in large-scale projects. Integrating BIM with Semantic Web technologies significantly enhances its potential by enabling more efficient automated compliance checking processes. The primary objective of this research is to underline the potential of integrating Semantic Web technologies with BIM methodologies for automated compliance checking. It aims to provide an overview of the affordances, potentials, and limitations of these technologies within the Architecture, Engineering, Construction, Operations (AECO) domain, offering professionals a comprehensive technological foundation on how Semantic Web technologies can be applied in combination with BIM methodologies. Within this scope, the paper particularly examines the use of Linked Data approaches of the Semantic Web, for automated compliance checking within the construction industry, by conducting a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The findings highlight four key approaches, namely Web Ontology Language (OWL), Semantic Web Rule Language (SWRL), SPARQL Protocol and RDF Query Language (SPARQL), and Shapes Constraint Language (SHACL). Notably, SHACL emerges as the most extensively adopted and suitable approach for automated rule verification workflows within the broader Linked Data paradigm, as well as being the latest recommendation by the World Wide Web Committee (W3C). However, the existing literature also underscores persistent challenges, including the frequent development of custom ontologies, limited reuse of validation rules, and the absence of standardized constraint libraries. Overall, the research findings demonstrated that integrating Building Information Modeling with Linked Data technologies establishes a robust foundation for extendible and automated compliance verification, contributing to the rapid digital transformation within the AECO domain.