sankalpsharmaa

Usc Econ Ai Workshop

Name: Usc Econ Ai Workshop
Author: sankalpsharmaa

Data community

SOURCE https://github.com/sankalpsharmaa/usc-econ-ai-workshop

Description

Materials and code from USC Economics Department AI workshops (Spring 2026). Hands-on sessions on GPT for data labeling, RAG, Cursor, and agentic coding with Claude Code.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

USC Economics AI Workshops

Hands-on sessions on AI tools for economics research, led by PhD students. Attendees apply the skills in real time rather than watching a lecture. Organized by David Schonholzer.

Fall 2026: AI Bootcamp

Two afternoons, August 24 and 25, 2026, two 50-minute sessions each day. Aimed at first-year PhD students and open to everyone else. Taught by Sankalp Sharma and Joshua Levy.

**Day 1, August 24.** Why a chatbot becomes "agentic", a shared vocabulary for the tools (context, `CLAUDE.md`, skills, rules, hooks, harness), and a live data-scraping demo built on SEC EDGAR.

**Day 2, August 25.** Gentzkow and Shapiro (2014) reread for a world where the research assistant is a bot, testing research code, git and version control, project directory structure, and building Claude artifacts to learn first-year material.

Slides and demo code: [`fall-2026/`](fall-2026/)

Spring 2026: Workshop series

Date	Time	Location
February 3, 2026	4:00–5:00 PM	KAP 319
March 24, 2026	4:00–5:00 PM	KAP 319

Workshop 1: February 3

**Neil He**: Using GPT as a Data-Labeling Tool for Economics Research Tutorial on using GPT via API to convert unstructured text into analysis-ready variables. Covers API calls, schema design, batching, and export.

**Daniil Sherstnev**: Retrieval-Augmented Generation (RAG) for LLMs Framework for grounding LLM outputs in a user-provided knowledge base to reduce hallucinations and enable access to local files and niche literature.

Workshop 2: March 24

**Joshua Levy**: Cursor for Economists: An AI-First IDE from RA to Referee Using Cursor across the research lifecycle: project scaffolding, data collection, custom ML tools, and producing reproducible exhibits.

**Sankalp Sharma**: Agentic Web Scraping with Claude Code Building web scrapers without writing code manually. Covers project initialization, dependency management, error handling, and supervising AI-generated code.

Slides and code: [`