Date
Publisher
arXiv
Generative Artificial Intelligence (GenAI) coding tools are transforming visualization education. They can assist with implementation and design, but they can also let students bypass intended learning trajectories. In this paper, we share our retrospective experience managing and teaching AI use in an upper-level visualization course. We implemented prompt injections, asked oral checkout questions, and taught two AI coding labs. Prior to our coding labs, at least half of the students had already used AI tools in their assignments. In both AI coding labs, refinement accounted for about half of students' prompting logs, and explanation was almost absent. In the lab where AI coding was optional, 44 of 78 (56.4%) submissions preferred the scaffolded instructions over designing their own prompts. Students' final projects were more polished than in our previous offering, but also more visually homogeneous. Our reflections point to the need for clearer AI use boundaries and instruction on prompting, and for teaching students to question generic AI designs and adapt them to their data and story.
Study at a glance
- Question: How can instructors effectively teach, manage, and evaluate student use of AI tools in a coding course?
- Setting and data: Upper-level undergraduate computer science visualization course, public university in the United States, Spring 2026, 87 enrolled students.
- Method: Descriptive and content analysis of student prompt histories, project artifacts, and observational reflections.
Why it matters
Generative AI can easily write code and complete assignments, challenging assumptions about student learning. Educators need strategies to manage AI use without outright banning it or allowing students to bypass learning trajectories.
Key findings
- About half of students' prompts in AI-coding labs focused on refining existing charts, while generating new code accounted for roughly one third of turns.
- Prompt injections in lab handouts occasionally caught policy violations, while oral checkouts helped students articulate and demonstrate their understanding of code.
- Although overall project visual polish improved with AI use, recurring design patterns emerged across projects, and the most AI-reliant projects clustered in the middle of rankings.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
