Basic programming, data structures, databases and scraping: the unglamorous plumbing that holds everything else up. The module teaches how to combine structured data and cross-reference it into analysis that means something, so that later modules can rely on clean, queryable inputs rather than isolated files.
F1
Module F1 of 10
AI Setups
Data as working material for design
3 ECTSOne fortnight6 sessionsOnline, live and recorded
The module
Gallery
Objectives
- To establish an operative understanding of language models, their limits and their cost.
- To configure a knowledge system for architectural practice.
- To acquire, integrate and verify data drawn from heterogeneous public sources.
- To model a project semantically, interrogate it in support of design argument, and build a reusable pipeline instead of one-off scripts.
What you will be able to do
Learning outcomes
By the end of the module, students will be able to anticipate the capabilities and limitations of large language models in architectural tasks and work efficiently with corpora that exceed model context limits through selection, decomposition and retrieval.
Professional outcomes
The module positions the architect as the practitioner capable of converting the dispersed knowledge of a studio into an asset the practice can interrogate.
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
data structuresversion control
Session by session
- Programming fundamentals for architects
- Data structures and modelling
- Databases and queries
- Scraping and public APIs
- Cleaning and cross-referencing
- Assembling a reusable pipeline
Deliverable
Deliverable F1: A reusable data pipeline of the student's own, documented and applied to their project.
Semantic model. Specific to this site and this city rather than generic. Entities and relationships defensible and serviceable for the questions posed. Merges with the cohort's shared schema.
Corpus and acquisition. Breadth and appropriateness of sources across more than one administration. Extraction reliability reported honestly. Reuse conditions established.
Integration and verification. Reconciliation decisions documented, including what remains unresolved and on what grounds. Verification adequate to the claims advanced.
Demonstrated value. The system answers questions previously unobtainable from the site material, and those questions merit asking.
Reproducibility and handoff. Executes from a clean clone and documented. The specification to F02 and F05 stated and testable.
Demonstrated value. The system answers questions previously unobtainable from the site material, and those questions merit asking.
Improvement required
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 →