Connects email history, ERP master data and Google Workspace activity in a knowledge graph to power AI search and relationship analysis.
Overview
An enterprise intelligence prototype that links information from several business sources so people and AI can search across them and understand organisational relationships.
Problem
Important context lives in email, ERP master data and workspace activity that are never joined, so relationship questions cannot be answered from any one system.
Solution
Integrate the sources into PostgreSQL and a Neo4j graph, then apply RAG and AI search over the connected data.
Architecture
Enterprise Knowledge Graph & Intelligence Portal architecture, top to bottom
01
Sources
Email history
ERP master data
Google Workspace activity
02
Integration
Enterprise data integration
03
Stores
PostgreSQL
Neo4j knowledge graph
04
AI layer
AI search
RAG
05
Portal
Intelligence portal
Relational storage in PostgreSQL alongside a Neo4j graph of entities and relationships.
GraphRAG-style retrieval is being explored on top of the graph and is project-level work.
Key features
Cross-source enterprise search
Organisational relationship analysis
Graph-backed retrieval for AI
Engineering challenges
Resolving entities consistently across email, ERP and workspace data.
Applying access control to retrieval across sensitive sources.
Results
No measured outcomes are published for this project. I only list results that have been verified.