AI-Assisted Coding Fundamentals

This unit introduces core concepts and hands-on practices for using AI tools to write, debug, translate, document, and maintain Python code. Students learn foundational machine learning, deep learning, and natural-language processing ideas while practicing prompt engineering, code formatting, testing, and tool comparison to prepare for more advanced AI-driven software development in later units.

Learning Objectives

• Analyze the capabilities, strengths, and limitations of AI code assistants and documentation bots (e.g., GitHub Copilot, Amazon CodeWhisperer, Tabnine) by comparing output quality, language support, and appropriate use cases for typical Python development tasks.
• Apply prompt engineering and interactive querying techniques to generate, translate, and refine Python code, including producing corrected syntax, formatted output, and unit-level test plans to validate functionality.
• Demonstrate understanding of machine learning, deep learning, and natural-language processing principles by explaining how these technologies power code generation, documentation, and NLP-powered developer tools and identifying common failure modes.
• Evaluate and classify software bugs and the four types of maintenance (corrective, adaptive, perfective, preventive), and produce a maintenance and test plan that leverages AI tools to automate formatting, documentation updates, and regression checking.