AI coding assistants can generate working code quickly, but working code isn’t necessarily correct code. In this course, discover a practical process for evaluating AI-generated Python code before relying on it in your projects. Join instructor Eduardo Corpeño, electrical engineer, computer programmer, and teacher, as he shows you how to use GitHub Copilot with a five-step framework: generate, inspect, test, verify, and improve. Explore practical examples involving intent mismatches, edge cases, hidden assumptions, fabricated methods, sensitive data, and incomplete test suites. Along the way, learn how to apply the complete evaluation loop in hands-on challenges and build a more systematic approach to reviewing AI-generated code before you use it.
