Glossary
Knowledge graph.
A connected map of the entities (people, projects, products, decisions) in your data and the relationships between them. Lets you answer questions that span multiple documents instead of retrieving just one.
Search returns documents. A knowledge graph returns answers that connect documents. When someone asks who owns the contract renewal for the customer attached to last quarter's launch, they need to traverse the graph. A flat document index can't do that. A graph can.
What this looks like in practice
Custom builds: six figures, six months.
Until recently, knowledge graphs were enterprise projects. Model entities by hand. Build ETL pipelines. Write the queries. Design the UI. Most companies couldn't justify the lift, so they bought search platforms and lived with the limitations.
The hard part: which connections actually matter.
Common entities flood every document. "The team." "Q4." Names of platforms everyone mentions. A naive graph treats every mention as a connection and floods retrieval with noise. The harder engineering is distinguishing genuinely central entities from commonplace ones, for THIS company's data specifically. Most off-the-shelf graph retrieval punts on this.
Queryable through chat and visualization.
Ask Lumen anything that spans multiple documents. Or open the visual graph view to see how everything in your company connects. The graph isn't a back-end. It's a surface.
The benefits of a knowledge graph, without building one.
Every serious AI product has a knowledge graph under it. Google, Apple Siri, IBM Watson, Microsoft Copilot. They're invisible infrastructure, but they're the difference between a system that searches and a system that knows.
Bring your knowledge.Simply ask.
CASA Certified · SOC 2 Infrastructure · GDPR-Aligned · Enterprise Ready