Syllabus
Claude Code for Accounting Research: AI Agents for the Empirical Researcher
This is a five-module, hands-on intensive (about three hours per module) plus a closing half-day seminar, built for accounting PhD students and faculty. It assumes mixed Stata/Python backgrounds and no prior experience with Claude Code or agentic AI tools. The course treats agentic AI as research infrastructure rather than as a chatbot. Over five modules you build real accounting pipelines on a free SEC dataset, EDGAR filing text, and WRDS data on your own account. You carry each one through to a verified, reproducible result rather than a one-off chat answer. Verification runs through every module, not just the last one, because an agent this capable is only useful for the parts of its work you have actually checked. The closing seminar steps back from the pipelines. It asks what this means for how accounting research gets produced and for the academic labor market that depends on it. You leave the course with working pipelines, a small personal library of skills, and a one-page position on your own comparative advantage that you are prepared to defend.
Format and audience
There are five build modules of roughly three hours each, and every one follows the same shape: a short lecture, a live demo (including a failure or two, and the recovery, shown live), a lab built on a starter zip with its own verify checklist, and a debrief with an exit ticket. Module 6 is different by design. It is a discussion seminar with no lab, built around a framing lecture and three structured questions. The audience is accounting PhD students and faculty; the material assumes comfort with either Stata or Python but no prior exposure to Claude Code, MCP, or any agentic tool.
Module by module
| Module | Title | Core question | Lab deliverable | Checkpoint |
|---|---|---|---|---|
| 1 | Foundations | What kind of tool is this, and how do I stay in control? | Install + a working CLAUDE.md + one verified task |
WRDS/Duo homework assigned |
| 2 | The Empirical Loop (SEC FSDS) | Can I go idea → verified figure, reproducibly? | FSDS pipeline + figure + replication README | Tunnel-status screenshot due |
| 3 | EDGAR Text → Data, + Skills | Can I build a text measure I’d defend to a referee? | 10-K panel + validity protocol + first SKILL.md |
WRDS fixes from the Module 2 checkpoint announced; last chance to get access working before Module 4 |
| 4 | WRDS MCP at Scale | Can Claude work my licensed data, safely, on my own account? | funda pull → Parquet/DuckDB/metadata (+ Stata extract) |
Tunnel teardown verified |
| 5 | Writing, Safety, Verification | What do I delegate, and how do I make my work auditable? | Capstone: a hardened Module 3 or Module 4 pipeline, scored against the rubric below | Module 6 readings distributed |
| 6 | Seminar: AI & the Research Market | What will I still be paid for? | One-page position memo (due one week after) | — |
Each build module follows the same template: 0:00–0:40 lecture, 0:40–1:15 live demo, 1:15–1:25 break, 1:25–2:45 lab, 2:45–3:05 debrief and exit ticket.
Assessment
- Per-module exit tickets (formative, not graded): one concept from the module, one thing that broke, and one thing you’d verify before trusting it, plus a module-specific question.
- Lab verify checklists: pass/fail, self-graded, spot-checked by the instructor.
- Module 5 capstone: you grade your pipeline pass/fail against the rubric on the Module 5 lab page, and I spot-check several projects live in the debrief. The rubric has three required sections and one stretch: reproducibility (does it rerun cleanly from the README in a fresh clone, is the commit history meaningful), verification (is the paper trail cross-checked against the actual commits, are two sanity checks sourced, is one number traced from raw data to output with nothing typed by hand), hygiene (do both credential-audit commands come back clean, is
.gitignorecorrect, is the tunnel closed, and did you delegate one routine writing task and write one meaningful one yourself), and, as a stretch, environment (a rerun inside a container with proof that access outside it is blocked). - Module 6 position memo: one page, “What I will still be paid for in 2036,” due a week after the seminar. It is graded credit/no-credit on defended specificity, not length. Commit to specific parts of the research process you believe stay human, defend the claim with at least one assigned reading and at least one concrete experience from the build modules, and close with one investment you will make in your remaining PhD years as a result.
Course policies
AI use. AI tools are the subject of this course and are permitted throughout it, including on the capstone. There is one exception: the argument in the Module 6 position memo has to be your own. Editor-not-rewriter-style assistance (see the Prompts page) is allowed even there. Disclose how you used it, following the disclosure norms discussed in the Module 6 seminar.
Data licensing. WRDS-derived data is never shared, posted, or committed to any repository, by the instructor or by students. Every pull happens on your own account, under your own institution’s license, and stays there. Your WRDS license already requires this; the course is restating it. The course’s public SEC data (FSDS, EDGAR) has no such restriction and is freely shareable.
Collaboration. Pair debugging during labs is encouraged. Talking through a stuck pipeline with a neighbor is a good way to practice, out loud, the judgment this course teaches. Graded deliverables (the capstone, the position memo) are individual.
Attribution. The course draws on cited external materials — see the About page for the full attribution note. The pipelines, skills, and written work you produce over the five modules are yours to keep, adapt, and publish.
Prerequisites and cost
You’ll need a laptop with admin rights (macOS or Linux native; Windows via WSL2), a working local Python installation before Module 1 (the labs and examples are in Python; bring R or Stata too if that’s your language, and Module 4 adds a Stata bridge), a Claude subscription or API key, a git and GitHub account, and a WRDS account with Duo enrolled. There is a hard checkpoint: a working ssh wrds connection by the end of Module 2, so that an account or Duo problem can still be fixed before Module 4 needs it. Full install steps, what a subscription costs at each tier, and the exact WRDS/Duo setup sequence are on the Setup and WRDS MCP Setup pages. Read both before Module 1. A pre-course email with the same checklist goes out about a week before the course starts.