Mindset and working environment. What a large language model is and is not: context windows, hallucination, coherence and persistence. Setting up the AI environment, from Python and dependency management to API keys, a scripting and automation environment, and MCP as the layer that connects models to the architect's tools: files, design software and geospatial databases. Prompting is treated as a practical skill, and each student builds a personal knowledge base with regulations, precedents and their own criteria that the AI consults while working. The module closes with a first simple agent applied to a real task.
F0
Module F0 of 10
Essential Workflows Overview
Mapping the territory before setting foot in it
Shared opening week · MCHOne fortnight6 sessionsOnline, live and recorded
The module
Objectives
- Understand what a language model can and cannot do in a design context.
- Set up a reproducible AI working environment.
- Build a personal knowledge base the AI can query.
- Deploy a first agent on a real professional task.
What you will be able to do
Learning outcomes
The student sets up and documents an AI environment, reasons about the limits of language models, structures a personal knowledge base and operates a simple agent applied to their own practice.
Professional outcomes
Enables the architect to introduce AI into daily studio work with criteria, and to become the person who sets up and governs that environment for a team.
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
context windowhallucinationversion controlknowledge base
Session by session
- What an LLM is and is not
- Environment setup and dependencies
- Prompting as a practical skill
Deliverable
Deliverable F0: A configured and documented environment (scripting environment, basic MCP and a Git repository), a personal knowledge base with at least ten of the student's own documents, and a first working agent applied to a real task.
Environment reproducible and documented.
Knowledge base structured and queryable.
Agent solves a real task end to end.
Critical reasoning about model limits.
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 →