Time to Build

You have the foundations. Now it is time to build.

In this module, you will use your coding agent — powered by the GraphAcademy MCP server — to build a GraphRAGRetrieval-augmented generation whose context comes from a knowledge graph, so the model can follow the relationships between facts. application against your Neo4j instance.

You will start with a short guided walkthrough to scaffold a working application and prove every piece is connected. After that, the build is open-ended: you decide what to build, and the tools are there to help you when you need them.

By the end of this module, you will have:

• Built a GraphRAG application connected to your Neo4j instance
• Used the GraphAcademy MCP server tools to model, query, and scaffold your application
• Seen first-hand how graph traversalFollowing relationships from one node to the next to reach other parts of a graph. gives an LLMA model trained on text to predict the next token, and so to generate language. richer, more accurate context