What Knowledge Graph does
Knowledge Graph provides a structured collection of enriched educational datasets that connects academic standards, curricula, and learning science data. It standardizes high-quality datasets with a unified schema, allowing edtech developers to focus on building AI-powered educational tools.| Dataset category | Description | Examples |
|---|---|---|
| Academic Standards | Hierarchical structures of state or national learning goals. | CASE Network 2 ↗‘s state standars |
| Learning Components | Academic Standards broken down into concrete skills or concepts. | Achievement Network’s learning components for K-12 math ↗ |
| Learning Progressions | Logical and usually sequential ordering of learning targets. | Student Achievement Partners’ Coherence map ↗ |
| Curriculum | Lessons, activities, materials, and assessments from publishers. | IM v.360® ↗ |
When to use Knowledge Graph
| Use case | Description | Examples |
|---|---|---|
| Align content to standards | Create content rooted in Academic Standards and learner competencies across subjects. | Replace fragmented infrastructure with a single, trusted source of standards data:
|
| Plan instructional content | Use dependencies (Learning Progressions) and granular skills (Learning Components) to inform instructional content and plans. |
|
| Compare standards across states | Use Standards Crosswalks to adapt content aligned to one state standard to other states’. | Outsource the burden of managing standards across states:
|
| Align content to curriculum | Create or use educational materials that are aligned to official curricula Contact us ↗ to get access to this gated functionality. |
|
| Deliver personalized assessments | Build adaptive experiences that go beyond content delivery into diagnostic assessment. |
|
How to access Knowledge Graph
Knowledge Graph is accessible in a variety of ways and is designed to be database-neutral, lightweight, and interoperable. The local files in particular can be used across graph databases, relational systems, in-memory tools, and AI pipelines without requiring any specialized infrastructure.| Access method | When to use |
|---|---|
| Local files | For offline access, custom processing, or complex queries across graph databases, relational systems, in-memory tools, and AI pipelines. Preserves the structure of entities and relationships, and supports both deterministic joins and AI workflows like embeddings or RAG. |
| REST API | For real-time programmatic access to data in an application |
| MCP server | For using natively with an LLM |
| Claude connector | For using Knowledge Graph directly with the Claude app |