Vocabulary tools for LangGraph Platform stateful workflows
The Scenario
LangGraph Platform is now GA — stateful workflows, human-in-the-loop, memory APIs. A developer builds a vocabulary tutor as a LangGraph stateful workflow: Word Orb, Lesson Orb, and Quiz Orb as three tool nodes. The knowledge graph routes between them. MCP integration means the agent discovers Orb’s tools automatically. Each response is deterministic JSON — the agent remembers what it taught and never contradicts itself.
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 LangChain
Three APIs map to three LangGraph tool nodes — dictionary, lesson, assessment — composable in stateful workflows with human-in-the-loop controls
MCP server at mcp.thedailylesson.com/mcp — LangGraph agents discover Orb tools automatically via the Model Context Protocol, zero manual registration
LangGraph’s memory APIs + Orb’s deterministic content = agents that remember what vocabulary they’ve taught and never repeat or contradict themselves
600+ LangChain integrations — Orb connects to the same ecosystem. Part of the Interrupt 2025 era of AI Agents