Skip to main content
Company knowledge and data · Knowledge graph

Link scattered knowledge
into a graph

Links database schemas, business policies and glossaries as nodes and edges. Agents follow the relations between nodes to explain how data and policies are connected.

Contact sales
Knowledge graph canvas
Knowledge graph canvasReal product screen
Knowledge graph

Link scattered knowledge
into a graph

Connect database schemas, operating rules and glossaries as nodes and edges. Agents follow the links to answer with the context between data and rules.

TableColumnConceptTermDocument

Select two nodes in turn to find the shortest path. Hover over a node to highlight its connections. Sample data from the example company ACME Logistics.

5node typesShortest paths · Cypher queriesApache AGE · Neo4j · Amazon Neptune
Real product screen
From a customer inquiry to a return request with path finding
What changes

Before and after adoption

Before

Few people know which column in which table relates to which policy.

After

Tables, columns, concepts, terms and documents are linked, and the path between two nodes can be found.

Before

AI does not answer well when a question takes several steps to work out.

After

The agent follows edges to find the relations, then answers.

Before

The same entity is registered more than once under different names.

After

Duplicate nodes are found and merged into one.

How it works

Four steps

01Connect sources

Connect databases and knowledge bases to build nodes and edges.

Node and edge counts of a knowledge graph
Key features

Knowledge graph in detail

Node and edge generation

Builds nodes and edges from databases and knowledge bases.

Path finding

Finds the shortest path between two nodes.

Queries

Finds the nodes and relations that match your conditions.

Duplicate merging

Finds nodes that refer to the same entity and merges them.

3 types of graph store

Supports Apache AGE, Neo4j and Amazon Neptune.

Connect to an agent

Connect a knowledge graph to an agent, and the agent follows relations to answer.

Admin settings

Settings each company configures

  • Connect the graph store to use.
  • Approve the node and edge generation rules.
  • Decide how widely to share the graph.
3Graph stores
5Node types (table, column, concept, term, document)
Path finding and queries

Figures reflect the product as of October 2026.

Related features

Related pages

Database queriesQueries business databases in natural language and answers with tables and chartsGlossaryTells the AI what your company's terms meanKnowledge search and cited answersAnswers with a cited source for every sentenceAgentsBuild AI assistants for each department
FAQ

Frequently asked questions about the knowledge graph

Do we need a separate graph database?

No. With Apache AGE, which runs on PostgreSQL, you do not need a separate graph database. Neo4j and Amazon Neptune can also be connected.

Does someone have to build the graph by hand?

No. The system builds the graph from databases and knowledge bases according to rules, and users review the rules and the results.

What kinds of questions does it work well for?

It works well for questions that require following relations across several steps, such as “Which policies does this column relate to?”

See it with
your own documents

In a consultation, we connect a few of your documents so you can check the answer quality for yourself. Send us your questions and our team will get back to you.

Contact salesRequest security documentation
Product videosReal product screens · Example company ACME Logistics · 16 videos