Three deterministic APIs for the AI agent stack — dictionary, lessons, assessments
The Scenario
162,250 words. 226,725 lessons. 21,900 assessments. 30,288 knowledge-graph connections. Three APIs that give any AI agent a verified vocabulary, a structured lesson plan, and an aligned assessment — deterministic JSON from the Cloudflare edge. Sub-5ms. MCP server live. Here is the complete cycle for one word: “design.” Written by engineers, for the 500K+ engineers reading TLDR AI.
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 explorer 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 TLDR AI
MCP server at mcp.thedailylesson.com/mcp — native integration with Claude Desktop, ChatGPT, Cursor, Gemini, and any MCP-compatible client
Built on Cloudflare Workers + D1 (SQLite at edge) + R2 (object storage) + KV — zero origin server, zero cold starts, sub-5ms p95 latency
Three APIs connected by a knowledge graph with 30,288 edges — Word Orb (dictionary), Lesson Orb (lessons), Quiz Orb (assessments)
Free tier: 50 calls/day, no credit card. npm: @lotd/word-orb. pip: orb-platform. Open-source SDKs on GitHub. 7M+ TLDR readers.