Agentic coding tools like Claude Code, Cursor, and Codex operate directly in your codebase, execute multi-step tasks, and maintain context across a project. Researchers can use them for ideation, downloading and cleaning data, running analyses, drafting papers, and many other tasks that make up the daily work of empirical research. This short course introduces these tools and shows how to integrate them into that work.

The course begins by explaining what makes agentic tools distinct from conversational AI and why that distinction matters for research workflows. Participants will then set up a working environment, including configuration files like CLAUDE.md and agents.md that shape how an agent behaves within a project.

From there, the course covers the broader ecosystem of plugins, MCPs, and skills that extend what agents can do. Participants will install pre-built plugins and skills relevant to empirical research, then learn to build custom skills that reflect their own analytic preferences, coding conventions, and writing voice.

The course also addresses how to work with agents responsibly. This includes breaking research tasks into structured plans, validating those plans before execution, and writing test scripts that verify agent output.

Participants will apply what they learn to research projects using real data and tasks drawn from empirical social science.