Course Schedule and Catalog

Department: Computer Science

Meeting: 4:00PM - 5:15PM TR (11-JAN-2027 - 23-APR-2027) 

Part of Term: Full Term

Grade Mode: Standard Letter

Course Type: Lecture

Language of Instruction: Taught in English

Distribution Group: Distribution Group III

Method of Instruction: Face to Face

Credit Hours: 3

 

Section Max Enrollment: 73

Section Enrolled: 0

Enrollment data as of: 2-NOV-2026 5:02AM

 

 

Final Exam: Scheduled Final Exam-OTR Room

 

Description: This course teaches students to steer AI agents through the full data science lifecycle. AI Agents include tools that can semi-autonomously write code, manipulate files, run analyses, and build applications from user-provided instructions. The course is organized around four modules. In the first module, students learn to use AI Agents for data manipulation tasks. These include acquiring, cleaning, and exploring datasets. This module includes a gentle introduction to the Python programming language and the Pandas library, focusing on high level functionality rather than syntax. In the second module, students direct agents to build and evaluate machine learning pipelines. A gentle introduction to machine learning models is provided along with the Scikit-learn and PyTorch frameworks. We will focus on a few use-cases within specialized domains and showcase how AI Agents can be applied to diverse machine learning problems. In the third module, students learn to leverage the inherent predictive and reasoning capabilities of AI models and integrate them directly in their data science workflows. In the fourth module, students experience deploying a data-driven demo application to a virtual private server through AI assisted coding and command line support. No prior programming experience is required. Students learn Python, bash and HTML through AI agents rather than as prerequisites to using them. The course is designed for students across disciplines—social sciences, natural sciences, engineering, and business—and emphasizes the judgment required to evaluate agent output, identify failure modes, and apply domain expertise where AI Agent suggestions fall short. Students work with multiple recently released tools throughout the semester, developing transferable skills for evaluating new AI tools as the landscape evolves.