Week 1: A question worth investigating
What could a corpus from your field tell you that you do not already know?
Design stage: Project setup and direction. Choose a topic, set up a project environment an AI agent and a human reader can both follow, and draft the direction of your project.
Prepare for class
Read: Chapters 1–2; the four stages of research design, and rules, memory, and knowledge. The chapters are in Canvas, and the companion page has the materials that go with them.
Reading focus: Read after Monday’s introduction, before Wednesday. In Chapter 1, follow how data management, concept representation, data analysis, and scientific communication depend on one another. In Chapter 2, separate rules (how an agent works), memory (where the project stands), and knowledge (what the project knows).
No technical preparation is required for Monday. Bring one or two topics you would like to study. Before Wednesday, try the companion’s setup guide and keep a note of anything that fails.
Weekly time budget
Outside class: 360 minutes (6 clock hours) maximum planned work per student. These allocations include all required preparation and submissions; they are planning estimates, not time logs for grading.
| Work | Planned minutes |
|---|---|
| Reading and discussion preparation | 90 |
| Exercises and project work, including troubleshooting | 210 |
| Writing, documentation, and reflection | 60 |
| Total | 360 |
Read Chapter 1 for the four stages and Chapter 2 for the framework. Use Wednesday’s setup session, and save an error for help instead of spending the week installing tools. Note one or two topics you could build a corpus on.
How the weekly cap works. If required work will exceed the budget, save your attempt and contact the instructor to adjust scope or arrange support.
From the book
Chapter 1’s last section includes three basic moves for working with an AI assistant, each with its own verification habit. Chapter 2 gives the project structure you will use all semester and names the three files to create first: AGENTS.md, memory/CURRENT.md, and kb/README.md.
On the companion website: Getting started · Chapter 2 project templates and recording · Project skeleton (zip)
Monday, January 11: Course introduction and the three basic moves
12:45–2:00 PM · PV A203
Tour the syllabus, the six milestones, and how the course uses the book and its companion website. Then try Chapter 1’s three basic moves on a paper from your own field: summarize and interrogate it, draft a literature search, and ask a model to critique a design. Name a topic and the audience that would care about it.
Check the reasoning: Each move has a verification habit. Ask the model to quote the passage behind each point in its summary, and check every claim you intend to rely on against the paper yourself. A summary that cannot point to its passages is one you cannot use.
Wednesday, January 13: Set up a project an agent can follow
12:45–2:00 PM · PV A203
Use the companion’s setup guide to get a working environment, in a browser notebook or locally. Download the Chapter 2 project skeleton, rename it, and begin the three files of the minimal starting point. Run a first OpenAlex query on your topic and look at what comes back. Use the session for setup help as needed.
Check the reasoning: Explain which file answers each question: how should an agent work here, what is the project doing now, and what materials should it use? The count from a first query is not yet a corpus. Read ten records before trusting it.
Work to carry forward
Keep the skeleton as your project folder from now on. Note what a first query returned for your topic, and one decision you already had to make about its boundary.
Coming up: Milestone 1: Project setup and direction (5 points), due Wednesday, January 27.
Assignments and deliverables · Your project · The book and companion website