AI-Assisted Code Quality and Tools

This unit explores how generative AI and related platforms can be used to improve software quality through refactoring suggestions, automated bug detection and fixing, test-driven development, and automated documentation. Students examine model capabilities and resources (e.g., AlphaCode, OpenAI, Bard, Dataset Search) and practice integrating AI-assisted workflows responsibly into development pipelines to prepare for final integration and deployment.

Learning Objectives

• Analyze outputs from generative AI models and platforms (e.g., OpenAI, Bard, AlphaCode) for correctness, explainability, and limitations, identifying instances that require human review or remediation
• Apply AI-driven refactoring suggestions, automated bug detection, and automated bug-fix techniques to an existing codebase, and produce or update unit tests following a test-driven development workflow
• Demonstrate how to generate and integrate visual documentation and automated API documentation using AI tools, and use dataset search resources to locate and cite relevant datasets and learning materials
• Evaluate trade-offs among AI tools, models, and tutoring versus automation workflows to select appropriate approaches that improve code quality while addressing ethical, reliability, and maintainability concerns