Khanmigo, Khan Academy’s GPT-4 Socratic tutor, guides a 7th grader through world history. The student encounters “civilization.” Instead of generating a definition that might be wrong or off-level, Khanmigo fetches a verified, age-calibrated definition from Orb Platform — then a structured lesson to teach the word in historical context, and a quiz to verify the student understood. The fact base is deterministic. The Socratic interaction is Khanmigo’s job.
Step 1 — Word Orb looks up the word
One API call returns a verified definition, translations, pronunciation audio, and etymology.
Loading word data…
Step 2 — Lesson Orb delivers a structured lesson
A 5-phase lesson (hook → story → wonder → action → wisdom) with the scientist teaching archetype.
Loading lesson data…
Step 3 — Quiz Orb assesses comprehension
Assessment questions aligned to the lesson content through the knowledge graph. Your agent tests what it taught.
Loading quiz data…
Step 4 — The Knowledge Graph connects everything
30,288 connections link words to lessons to assessments. Every quiz question tests what the lesson taught.
Loading knowledge graph…
Why this matters for Khan Academy
Age-calibrated definitions (kid, teen, adult, elder) give Khanmigo reading-level-appropriate content to cite — not generate
47-language translations support Khanmigo’s global expansion to India, Spanish-speaking markets, and the free-for-teachers initiative backed by Microsoft Azure
5-phase lesson model (hook → story → wonder → action → wisdom) maps directly to structured classroom instruction — complements Khanmigo’s Socratic dialogue
Image upload tutoring: student photographs a word, Khanmigo fetches the verified definition from Orb instead of generating one — 162,250 words across all K-12 subjects