Effective Coding with AI
Course ID 15113
Description This application-focused course will teach students how to effectively combine intermediate programming skills with contemporary AI tools to enhance their software development workflow. Students will explore the capabilities and limitations of current AI coding assistants, experiment with prompt engineering, and collectively develop standards for maintaining code quality, transparency, and ethical integrity in AI-augmented workflows. The course will also feature seminars from AI experts in industry and academia. Through weekly coding projects, students will rapidly build complete applications while balancing creative problem-solving with rigorous quality assurance. A collaborative approach emphasizes peer learning, with students sharing discoveries and contributing to evolving best practices for prompting and evaluating AI-generated code, ensuring proper attribution, and establishing transparent development protocols. These projects are also designed to jump-start students' portfolios for future employment. By completion, students gain practical development experience with AI tools and will contribute to evolving best practices for future courses, learning from both instructors and peers' experiences with these rapidly advancing technologies."
Key Topics
Using AI assistants, AI-assisted project development, responsible use and ethical transparency, testing and quality assurance
Required Background Knowledge
Algorithmic problem-solving skills, intermediate programming experience 15-112 or equivalent
Course Relevance
Undergraduate and graduate students with intermediate programming experience (15112-level)
Course Goals
By completion, students gain practical development experience with AI tools and will contribute to evolving best practices for future courses, learning from both instructors and peers' experiences with these rapidly advancing technologies.
Learning Resources
Python 3.12, Visual Studio Code, various contemporary coding platforms and assistants (ChatGPT, Claude, Copilot, Codex CLI, etc)
Assessment Structure
"Homework: 20%
Participation/Critiques: 20%
Projects: 40%
Exams: 20%"
Extra Time Commitment
NA
Course Link
https://www.cs.cmu.edu/~mdtaylor/113/