By Daniel de Angulo, Product Manager, Learner Experience at Khan Academy
Khan Academy’s new AI-powered tutor and teaching assistant, Khanmigo, is a groundbreaking platform that provides high-quality, on-demand tutoring to help kids catch up, review, or accelerate ahead. But how can we teach an AI program to learn like a human being? Enter prompt engineering—the art and science of crafting precise inputs to guide AI responses. In this deep dive, we’ll explore our seven-step approach to crafting prompt engineering.
1. Understanding the ideal student-teacher relationship
The gold standard of education has always been one-on-one tuition. In 1984, Benjamin Bloom found that personal tutoring could significantly boost a student’s performance, but he called it the “2 Sigma Problem” because it has always been too costly to offer this level of attention to everyone. We at Khan Academy believe that AI will help bridge this gap. Khanmigo is one of the tools we use to personalize learning for all students. In order to achieve prompt engineering, we must first understand the relationship between tutor and student. We visualize the perfect interaction between tutor and student. What would it…
