Using AI for Academic Research - CBS Workshop Workshop by Professors Jesse Schreger and Malek Ben Sliman
Following in the footsteps of a very successful workshop on accelerating academic research with AI by Santiago Balsiero and a couple of his colleagues at Google (recording and slides will follow soon), we are planning a series of additional workshops on using AI for academic research in the summer and fall.
Our next workshop is a two-session workshop led by, our very own, Professors Jesse Schreger and Malek Ben Sliman. The first session (June 24) will focus on an introduction to AI tools for academic research (with an emphasis on Claude). The second session (July 27) will build on the first session and will serve as a hands-on workshop where faculty and doctoral students can bring their own research ideas and data sources to advance their research project, with guidance, during the workshop (see details below). We will record this two-session workshop and possibly repeat it in the fall, if there is sufficient demand, for those who missed it over the summer.
Looking forward to seeing over the summer in these workshops,
AIB and VDR
Session 1 – Introduction to Using AI Tools For Academic Research – June 24 2:00-4:00pm
Summary: In this session, we will cover installing and configuring Claude Code, the different ways to work with it (terminal, IDE integration, GUID), pricing and Columbia's access, model selection, and the key operating modes (plan, accept edits, auto, skip-permissions). We'll address data sharing and privacy concerns. We will demonstrate how to integrate Claude Code to your workflow across different programming languages (i.e. R, Stata, Python). We will also discuss version control and how to utilize git with Claude.
In addition, we will provide suggested “assignments” for coming prepared with your own data to execute your own research in the second session.
Takeaways: The goal is to walk out with Claude Code installed and integrated into a research workflow alongside existing tools (Stata, R, Python), with a clear sense of how to start using it for one’s own research.
Who is this for: this session is primarily designed for faculty who haven't yet integrated Claude Code into their day-to-day. Heavier users are welcome but might find session 2 more useful. Those who skip this introductory session should make sure they are prepared to participate in the second session.
Session 2 – Using AI in Your Research – July 27th 11:00am-4:00pm
Summary: In this session, faculty will execute their own research in real-time using AI tools. Participants will share their ongoing progress and challenges with the group throughout the session. The goal is to see how close to a real research result participants can get during this extended workshop.
In addition, this session will introduce more advanced ways to Claude Code in research. Specifically, we will discuss how to extend Claude Code with MCPs, subagents, skills, plugins and API calls. We will help participants learn to work remotely and collectively using Claude Code (e.g., remote control, Claude in the Grid, tmux/zellij/cmux). This is an interactive workshop and time will be provided to help troubleshoot any issue one might encounter.
Takeaways: The goal is to leave the workshop knowing how to produce original academic research with an agent-based workflow. Ideally, some of you will even have a new result to build on for a full academic paper.
Who is this for: Anyone interested in using AI for research. We hope that advanced users also attend to share their workflow and discuss research methods with their colleagues.
