Syllabus
Schedule
| Topic | Lec | Lab |
|---|---|---|
| Module 1: framing & reading | ||
| what this course is | Sep 15 | Sep 17 |
| reading matters | Sep 22 | Sep 24 |
| Module 2: build & craft | ||
| why (still) build from scratch | Sep 29 | Oct 1 |
| specs before prompts | Oct 6 | Oct 8 |
| git makes a diff | Oct 20 | Oct 22 |
| the abstraction ladder (of programming) | Oct 27 | Oct 29 |
| Module 3: data & evaluation | ||
| outsourced data | Nov 3 | Nov 5 |
| the machinery beyond vanilla transformers | Nov 10 | Nov 12 |
| evals as experimental design | Nov 17 | Nov 19 |
| auditing the artifact and the judge | Nov 24 | none, Thanksgiving |
| Module 4: reflection & synthesis | ||
| what the (human) tutor had | Dec 1 | Dec 3 |
| closing arguments | Dec 8 | Dec 10 |
- The first meeting is the September 15 lecture.
- Tuesday October 13 runs a Monday schedule. That week has no lecture, and its lab is cancelled.
Learning objectives
The takeaways stack in order:
- how to use AI tools;
- where and why these tools work well (building on the prerequisites);
- where and why these tools fail by construction (the machinery beyond vanilla transformers and the programming-abstraction hierarchy);
- how to orchestrate work around the tools based on that why-and-why-not understanding (what to delegate, what to keep, how to verify the result, and what evidence supports those choices).
More concretely, students should be able to:
- specify and decompose work for an AI agent: e.g., specs first, scoped increments, skills as reusable contracts;
- keep the work inspectable: e.g., version history and provenance for AI-co-authored code, context held to a budget;
- form and test mechanism hypotheses for model failures: e.g., training objective, context limits, sampling;
- judge data and design evaluations: e.g., contamination checks, sample size, auditing the judge itself;
- check an AI-assisted reading against the primary source: e.g., what was inserted, what was dropped, where the delta went;
- write up a result as claim, evidence, and limits, and edit AI-drafted prose without losing authorship;
- justify their delegate, verify, redirect, and decline calls with evidence: e.g., a transcript moment, a commit.
Page updated August 1, 2026.