AI in CS Education

Demystify, Use, Reflect: Preparing Students to Be Informed LLM-Users

SIGCSE 2026 poster and course materials for helping students engage with large language models critically, confidently, and responsibly.

Team

Photo of Nikitha Chandrashekar
Nikitha Chandrashekar
Student Researcher
Photo of Sehrish Basir Nizamani
Sehrish Basir Nizamani
Faculty – Computer Science
Photo of Margaret Ellis
Margaret Ellis
Faculty – Computer Science
Photo of Naren Ramakrishnan
Naren Ramakrishnan
Faculty – Computer Science

Overview

This work presents a set of teaching strategies and course materials designed to help computer science students become informed and reflective users of large language models (LLMs). Rather than treating LLMs as black-box helpers, the materials invite students to understand how these models work, when they are helpful, where they fail, and how to integrate them thoughtfully into their problem-solving and learning practices.

The materials on this page are shared to support instructors who wish to use them in their own courses. They are licensed openly under CC BY-NC-ND 4.0 and may be reused with attribution for non-commercial purposes, but may not be altered or adapted.

Poster

You can download the SIGCSE 2026 poster here:

Course Materials

These materials were developed for use in CS 2104: Problem Solving in Computer Science and focus on helping students:

  • Understand the basic ideas behind LLMs
  • Use LLMs to support (not replace) their own reasoning
  • Engage in structured reflection about AI use in coursework
  • Recognize limitations, bias, and hallucinations

Curriculum Design Team

  • Margaret Ellis (Curriculum Designer, Instructor of Record, Slide/Content Developer)
  • Naren Ramakrishnan (Curriculum Designer, Course Consultant)
  • Sehrish Basir Nizamani (Curriculum Designer, Slide/Content Developer)


Teaching Materials by Week

Week 1

Focus: AI literacy · Prompting · Course navigation · Syllabus understanding

Week 2

Focus: Transformers · Tokenization · Self-attention · LLM fundamentals

Week 3

Focus: Algorithmic thinking · Flowcharts · Python basics · LLM-supported debugging

Week 4

Focus: Strings · Regex · Substring algorithms · Problem-solving patterns

Week 5

Focus: Recursion · Backtracking · Dynamic programming · Algorithm correctness · LLM-assisted problem solving

Week 6

Focus: Software engineering · Requirements · Design · LLM-assisted development

Week 8

Focus: Version control · Git workflows · Collaboration skills

Week 9

Focus: Networking · Internet architecture · Data centers · TCP/IP layers

Week 10

Focus: Human-Computer Interaction . Usability Evaluation

Week 13

Focus: Data Science · AI reliability · Ethics in coding workflows

How to Use These Materials

These resources are designed to be modular. You can:

  • Adopt the full set into a dedicated AI-and-problem-solving module
  • Pull a single assignment or activity into an existing course unit
  • Use the slides for a guest lecture or one-off session on LLMs

Unless otherwise noted, all materials on this page are shared under the Creative Commons Attribution–NonCommercial–NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).

You are free to:

  • Share – copy and redistribute the material in any medium or format
as long as proper credit is given, the materials are not used for commercial purposes, and no modifications, adaptations, or derivative works are made.

Recommended Citation

If you use or reference these teaching materials in your own courses, publications, or talks, please cite:

Ellis, M., Ramakrishnan, N., & Nizamani, S. B. (2025). Demystify, Use, Reflect: Teaching Materials for Supporting Informed LLM-Use in Computer Science Courses. Retrieved from https://people.cs.vt.edu/sehrishbasir/coursematerials2026.html

@misc{llm-materials-2025, title = {Demystify, Use, Reflect: Teaching Materials for Supporting Informed LLM-Use in Computer Science Courses}, author = {Ellis, Margaret and Ramakrishnan, Naren and Nizamani, Sehrish Basir}, year = {2025}, howpublished = {Course materials}, note = {Available at https://people.cs.vt.edu/sehrishbasir/coursematerials2026.html} }

Acknowledgements

This work was supported by the CETL Instructional High Impact Project Grant. We gratefully acknowledge this support, which made the development and dissemination of these teaching materials possible.

Contact

For questions about these materials or collaboration inquiries, please contact:

Sehrish Basir Nizamani
Department of Computer Science, Virginia Tech
Email: sehrishbasir@vt.edu