Context layer vs semantic layer vs code and data graph

Semantic layers, context layers, and code and data graphs provide different kinds of information to AI agents beyond raw data tables. A semantic layer standardizes business metric definitions such as revenue or churn for analytics and text-to-SQL use cases, while a context layer expands on this with catalog metadata, documentation, ownership, quality indicators, and access rules to help agents understand and appropriately select data. A code and data graph is derived directly from source code across repositories and languages, mapping how tables and columns are read or written so coding agents can assess the impact of proposed changes. Organizations may use multiple layers: semantic and context layers are suited to business-question and analytics agents, whereas code and data graphs support code-writing and review agents by exposing dependencies that metadata alone may not reveal. Foundational positions its Context of Code and Data product as a code and data graph delivered through MCP for coding tools such as Claude Code, Cursor, and Codex.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.