Vocabulary infrastructure for the universal AI assistant
The Scenario
Google Assistant is transitioning to Gemini throughout 2026 — a universal AI assistant powered by Gemini 2.5 Pro. A Gemini extension teaches a “word of the day.” Today: “legacy.” Gemini fetches the verified definition from Orb Platform, delivers a 60-second lesson using the empath teaching style, and asks a comprehension question — deterministic content that Gemini can cite, not generate.
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 empath 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 Google Gemini
Gemini’s universal assistant vision needs structured, verified content — Orb provides the vocabulary ground truth that Gemini can cite across devices
Project Mariner’s tool-use capabilities can call Orb’s API directly for on-demand vocabulary instruction via the Gemini API
5-phase lesson model (hook → story → wonder → action → wisdom) structures a 60-second voice learning experience across phones, speakers, and smart displays
162,250 words means Gemini can serve a new word every day for 444 years — deterministic content across the Assistant-to-Gemini migration