Every piece of graded work in the course, what it is worth, and when it is due.
Assessment#
Two builds and a written audit, each weighted toward the same skill the course is teaching: reading a predictive system’s behaviour closely enough to say something specific about it. The weights below sum to 100 and don’t change once teaching starts.
Assignment 1: Build a predictive input system
A working predictive-text build in a domain of your choice, submitted with a short written account of exactly where and why it fails
Due 26 March 2027 · Weight: 25%
Assignment 2: Audit a deployed suggestion feature
A comparative audit of a real, currently deployed prediction or suggestion feature, using the fixed-input method practised across weeks 6 through 9
Due 7 May 2027 · Weight: 35%
Final project: The full audit
The capstone — take Assignment 2's audit and turn it into a complete, standalone case study of a real product's suggestion design
Due 28 May 2027 · Weight: 40%