FOUNDATIONS
Student Portal
WEB AI Canvas
F9
Module F9 of 10

AI Integration

A bespoke, adaptive multimodal ecosystem

3 ECTSOne fortnight6 sessionsOnline, live and recorded

The module

The module develops a critically grounded final project by placing the programme’s accumulated production in a shared field of relations. A custom-built tool combines semantic models and quantitative evaluation, collecting the students’ work into a single combined map. The quantitative and semantic relationships allow for an AI-mediated crit that generates questions and conversations between students, rather than ranking work. Students will first consolidate their personal knowledge bases so they can be used as an operative device for their final project: Those bases will serve as a personal customization for integrated, predominantly agentic workflows. A case might retrieve site data from a mapping platform, cross-reference it with environmental sources and pass selected outputs into ComfyUI and create preliminary visualizations.

Objectives
  1. Consolidate previous work and references into an operative personal knowledge base.
  2. Adapt integrated agentic workflows to specific architectural questions.
  3. Use AI-mediated comparison to generate relations, questions and dialogue.
  4. Develop, document and defend a coherent final project through tailored tutoring.

What you will be able to do

Learning outcomes

Students will be able to curate and activate a personal knowledge base for retrieval, comparison and project development; translate an architectural question into an appropriate combination of agents, models, datasets and design tools; evaluate their outcomes through appropriate user-defined metrics, either with semantic analysis and similarity measures, or geometry-based analysis; using them to formulate questions and relationships; and develop, document and defend an open-format final project with a clear position, references and internal coherence.

Professional outcomes

Leaves the architect with an operating system for their own practice, a personal knowledge base, together with the ability to grow it further and steer it for each commission or research question.

Methodology

Learn by doing, on the student's own real project. No software tutorials: a pre-built starting package is provided and base resources are given apart. Sessions combine a short input, guided practice and critique.

Concepts
Integrated agentic workflowsVector databaseAI-mediated architectural critQuantitative evaluationPersonal knowledge baseDimensional reductionHuman oversight

Session by session
  1. Consolidating the Knowledge Base
  2. AI-Mediated Crit: Previous Production
  3. Defining the Final Project + Project Workshop
  4. Project Workshop
  5. Project Workshop
  6. Final Presentation and Collective Crit

Deliverable
Deliverable F9: An open-format final project developed through a deliberate combination of architectural and AI-based methods, accompanied by an operative personal knowledge base containing selected previous work, references and project material; documentation of the project-specific workflow, including sources, agents, tools, handovers, transformations and points of human oversight; a concise dossier stating the project’s question, position, references and criteria; an iteration record showing significant alternatives, decisions and discarded directions rather than an exhaustive log; relational documentation produced through the shared system, such as a panel connecting the project with several projects or references through an explicit argument; and a public presentation and defence of the project, process and criteria. Connections to previous modules must be purposeful and legible: the number of tools used is not an indicator of integration or quality.
The project is relevant, coherent and critically grounded.
The workflow is purposeful; authorship and oversight remain explicit.
The knowledge base, criteria and development process are legible.
The presentation and relational documents sustain collective discussion.

Faculty and resources

Module Faculty

Learn this in MIAWS

This module is part of the 18-week postgraduate program. Work with your own real project from week 1. First cohort February 2027.

Talk to MIAWS AI →

Explore More

← All 10 Modules → All Faculty → About the Program → Apply → FAQ