John Barrios · Yale School of Management

Claude Code for Accounting Research

A hands-on PhD course on agentic AI for empirical accounting research, with five build modules and a closing seminar. It starts at first install and ends at a verified WRDS-to-Stata pipeline. The seminar then discusses what these tools mean for the profession.

6 modules · 5 labs · 41 skills · 1 verification protocol

Each of the five build modules runs about three hours: a short lecture, a live demo, an extended lab and a debrief. Each one ends with something you keep, such as a reproducible pipeline, a publication-style figure, a text-extraction skill, or a regression-ready Compustat extract on your own WRDS account. Every module covers speed, but it also covers what you need before that speed is usable in a paper: verification, paper trails, credential hygiene, and judgment about whether a measure is valid, which no agent supplies. Module 6 is a discussion seminar on AI, the production of knowledge, and the academic research market. It ends with a position memo instead of a lab.

The course assumes no Claude Code experience. It does assume a laptop you control, a working WRDS account, and that you are willing to run code live.

The six modules

Module 1

Foundations

What kind of tool is this, and how do I stay in control?

Module 2

The Empirical Loop

Can I go from idea to verified figure, reproducibly?

Module 3

EDGAR Text → Data, + Skills

Can I build a text measure I’d defend to a referee?

Module 4

WRDS MCP at Scale

Can Claude work my licensed data, safely, on my account?

Module 5

Writing, Safety, Verification

What do I delegate, and how do I make my work auditable?

Module 6 · Seminar

Seminar: AI & the Research Market

What will I still be paid for?

Beyond the modules

The Skills catalog has 41 agent skills for accounting research, covering econometrics, data work, writing and review. Each has a download and a one-line install command. The Tools guide compares Claude Code with Claude Desktop, Cursor, and Codex, and includes a decision table for choosing one for each task. The Prompt gallery collects every reusable prompt the course teaches. The Verification protocol is the one-page checklist you practice in every module. Resources lists other useful tools and readings, grouped by the module where each is most relevant.

Taught by John Barrios, Yale School of Management. Course materials draw on outside sources, which are credited on the About page. All student-facing content is original.