F0
Foundations (Mindset, Environment and AI Workflows)
The module starts with a guiding question: what can AI do that is useful for your specific practice, and what can't it?
Language models don't think or design. They predict, suggest, and execute with consistency and speed. Understanding how an LLM works, what context is, why they hallucinate, and when an image model produces what you expect — is what enables using them well. Without that framework, use oscillates between disappointment and uncritical dependency. The second part builds the working environment: Python
Deliverable F0: Configured and documented environment (Claude Code + basic MCP + Git repository), personal knowledge base with at least 10 own documents, and a first functional agent applied to a real task.
F1
Territory with AI (AI-driven territorial strategies)
The architect's work starts before design: understanding the place, urban context, regulatory constraints, and site opportunities. This module is about how AI transforms that reading and analysis phase.
A pipeline is built that queries public APIs (land registry, topography, Copernicus, OpenStreetMap), processes the data, and automatically generates site analysis: land uses, applicable regulations, surrounding urban fabric, sun conditions. A language model reads that data and produces an interpretive report: what patterns exist, what restrictions apply, what opportunities the place offers. The sa
Deliverable F1: Automated territorial analysis pipeline applied to a real site of the student, with AI-generated interpretive report and 3D context model integrated in the design environment.
F2
Modeling with AI (Capturing and Modeling with AI)
The module works the step from the physical world or a reference to useful 3D geometry, and how to generate or modify geometry from natural language.
The first part covers capture: 3D reconstruction from video or images with neural rendering techniques (Gaussian Splatting and similar). The result is a model directly integrable into the design workflow without the intensive post-processing of traditional photogrammetry. The second part covers language-assisted modeling: the architect describes what they need (adjusting an envelope to site constr
Deliverable F2: 3D capture model of a real space integrated in the design environment, and a natural language-assisted modeling exercise applied to an element of the student's project.
F3
Design with AI (AI-assisted Parametric Design)
This module works the core of the design process: exploring alternatives, generating variants, and evaluating options against multiple criteria.
Parametric design has been restricted to those who mastered visual programming. AI changes that equation: the architect describes the system they need (a facade with gradient variation, a roof system responding to site geometry, a program distribution optimizing surfaces and access) and the implementing code is generated, tested, and documented. On that base, the module introduces generative desig
Deliverable F3: Parametric system co-developed with AI for a real element of the student's project, with generative exploration of alternatives evaluated against own criteria and visual synthesis of results.
F4
Simulation with AI
Many high-impact design decisions are made without sufficient data on building behavior. AI enables that data to arrive earlier, with less technical friction and in an interpretable format.
The module works a pattern common to all simulations: connecting project geometry with an analysis engine, running the simulation, and translating numerical results into concrete recommendations via AI. Applied to different domains depending on the student's project: bioclimatic (sun, radiation, comfort, ventilation), structural (schematic FEM model, stresses, variants), natural lighting, acoustic
Deliverable F4: Simulation pipeline applied to at least two relevant domains for the student's project, with AI-generated results report and design recommendations.
F5
Communication with AI (Image, Video, Immersive Environments with AI)
The module works the production of project images, video, and real-time immersive environments with AI integrated in the visualization pipeline. Three levels are worked:
Level 1 — Concept image/video: without detailed geometry, AI generates images communicating character, atmosphere, and intention. Useful for early exploration and client communication before committing to a form. Level 2 — Image/video with geometric control and consistency: the 3D model guides AI generation, which adds materials, lighting, and atmosphere without manual texturing or lighting. Contr
Deliverable F5: Immersive environments, videos, and images of a real project at all three levels, with visual coherence between them.
F6
Documentation with AI (BIM Documentation, Project Management, Information Management)
An architect produces documentation in all project phases: descriptive reports, technical specifications, licensing files, meeting minutes, construction reports, delivery documentation. Most is written from scratch each time, from data that already exists in the model, notes, or client conversations. This module works how AI automates that production.
The pattern is always the same: there is data (model, reports, notes, regulations, comparisons, administrative and executive communications) and a document to produce. AI connects both. Applied to: descriptive reports, technical specifications from the BIM model, regulatory compliance verification, quantity extraction for budgeting, minutes from meeting notes, and administrative correspondence. Al
Deliverable F6: Descriptive report, automated specifications of at least two building systems, and regulatory verification report generated with AI from project data, plus demonstration of conversational query to the BIM model.
F7
Fabrication with AI (Advanced Digital Fabrication, Robotics, Complex Special Parts and Assemblies)
This module works the transition from digital model to physical component when AI is an active part of the fabrication process. Not learning robotics as an isolated discipline, but understanding how the constructive detail changes when geometry, tool, movement, and assembly are integrated from the start in an intelligent parametric system.
The central question is how to design for fabrication when AI intervenes in the definition of form, material, tolerances, and machine path. Robotic fabrication, CNC, and 3D printing are not separate courses — they are contexts where the same parametric-AI design logic is applied to different production constraints.
Deliverable F7: Development of a parametric detail or system oriented to advanced fabrication. Machining and assembly simulation with AI integration. Documentation of the design-fabrication process and decision analysis.
F8
Integration with AI (Own Adaptive Ecosystem)
The final module introduces no new tools. It works how to connect everything built in previous modules into a coherent working ecosystem, adapted to the student's specific practice.
The central question is how the workflow functions when AI is integrated: what tasks are automated and which aren't, what agents are configured and for what type of commissions, where the architect's supervision enters and where it's not needed. Part of that system is the studio knowledge base (regulations, reference projects, construction details, own criteria), integrated in a RAG system so mode
Deliverable F8: Project developed with AI integrated in process stages. Documentation of the working system: agents, knowledge base, flows and adaptive prompts. Presentation of the project and its process.