...

When an AI agent is asked why profit fell last quarter, it can report the correct figure and still blame the wrong cause. Governed semantics make the number accurate, but the explanation depends on how the business works, and that knowledge is rarely recorded anywhere an agent can read. A context graph makes it explicit, so AI agents can explain why a metric moved.

What is a context graph?

A context graph connects business entities, metrics and concepts through typed relationships that carry rules, conditions and metadata. Some enterprise implementations, such as Kyvos’ business context graph, also model causal links and weights, so an agent can tell which relationships drive a result and which matter most. At query time, AI agents use these connections to identify relevant data and see how the pieces fit together.

The term context graph is still evolving, and vendors use it for different kinds of information, including data lineage, permissions and decision history. In analytics, a context graph focuses on business measures: which KPIs drive others, in which direction and under which conditions.

Why does enterprise AI need a context graph?

Enterprise AI needs a context graph because explaining a business result depends on relationships that raw data and metric definitions do not record.

Consider a retailer whose profit falls while sales rise. An AI agent can read both metrics correctly and still miss that discounts are reducing profit, that mass-market customers respond to discounts and that premium customers respond little. Without these relationships, the agent can recommend extending the promotion to every segment, against pricing policy.

A context graph records each relationship with its conditions attached, so the agent limits the promotion to the segment that responds.

What does a context graph comprise?

A context graph comprises nodes, which represent what matters to a task, decision or action, and the relationships that connect them. For enterprise analytics, nodes fall into four types:

  • Metrics: KPIs such as sales, profit, discount and return rate
  • Entities: customers, products, channels and regions that metrics are analyzed by
  • Business concepts: business goals no single metric captures, such as profitability
  • Supporting knowledge: playbooks, policies and source systems an agent checks alongside the KPIs

Relationships are the core of the graph. They record how one node influences, owns, uses or depends on another, and each one carries the rules and conditions that decide when it applies. Here’s how:

  • A concept or metric is defined by the metrics behind it, such as profitability by profit and cost, or sales by units sold and price
  • A metric breaks down by entities, such as sales by region or customer
    • One metric drives another up or down, such as discounts reducing profit
  • Chained together, these links form causal paths from a result back to its causes
  • A metric links to its source, such as a pricing playbook

Nodes and relationships also carry:

  • Conditions that decide when a relationship applies, such as discounts lifting sales for mass products
  • Weights that rank competing drivers when several could explain a change
  • Rules the agent follows, such as which driver to check first
  • Source bindings that map metrics and entities to their governed definitions

What does a context graph look like?

A retail context graph with KPIs, entities, a business concept and external sources linked by typed, weighted relationships

A retail example: profitability depends on sales, profit, discounts and costs, and each arrow shows how one metric affects another

How is a context graph different from an ontology and a knowledge graph?

Ontology Knowledge graph Context graph
What it is A formal model of a domain’s concepts, properties and constraints A graph of real entities and facts, structured by an ontology A graph of relationships with the rules and conditions that apply to them
Question it answers What is a customer, and how can it relate to other concepts? What is connected to what? What drives this result, and what applies here?
How it reasons Formal logical inference from defined rules and constraints Traversal across connected entities and facts Following drivers and conditions from a result back to its causes
Example Every customer belongs to one segment, and a discount applies to a product Customer 1042 is in the premium segment and bought product B at a 10% discount Discount amount reduces profit, and its effect on sales depends on customer segment
Where is it applied Implemented through a knowledge graph or a context graph Record-level analysis, such as linking shared accounts to expose a fraud ring Enterprise AI analytics on governed metrics, such as explaining why profit fell and what to do next

How does Kyvos implement context graph and deliver complete, connected business context for AI analytics?

Kyvos’ business context graph builds on Kyvos semantic models. It connects governed metrics to business entities, concepts and external entities through typed relationships, such as ‘has primary’, ‘decomposes into’, ‘segmented by’, ‘positively influenced by’, ‘negatively influenced by’, ‘belongs to’ and semantic relationships that teams name with verbs, such as ‘buys or sold in’. Relationships carry rules and weights, and influence relationships form causal paths across multiple semantic models.

AI agents assemble context for each query from semantic models, the business context graph and integrated policies, procedures and documentation. Governance is built into every component, and every metric in a causal path carries one approved definition, so AI answers stay accurate and consistent.

To see how business context graph works for enterprise AI, talk to a Kyvos expert.

Frequently Asked Questions

Is Kyvos’ Business Context Graph a knowledge graph?
The Kyvos Business Context Graph is a context graph for enterprise analytics. Like a knowledge graph, it connects entities through relationships. However, it also adds the rules, conditions, weights and causal paths AI agents need to explain business results.
How does a context graph improve AI accuracy and reduce hallucinations?
A context graph improves AI answer accuracy by giving agents documented drivers to follow when they explain a result. Explicit relationships leave fewer causal connections for the agent to guess, which reduces hallucinated explanations.
Does a context graph replace a semantic layer?
No. A context graph builds on a semantic layer. The semantic layer governs what each metric means, and the context graph records how those metrics affect one another.
Can a context graph help build an ontology?
Yes. In enterprise analytics, governed semantic models define business concepts and a context graph defines the relationships and rules between them. Together, they form an ontology of the analytics domain.
Can one context graph cover several business domains?
Yes. One context graph can connect KPIs across domains such as sales, operations and customer experience, so an AI agent can follow a cause from one domain to another.
How is the Kyvos Business Context Graph different from other context graphs?
Many context graphs focus on metadata, data lineage or decision history. The Kyvos Business Context Graph focuses on how governed business metrics drive one another, and every relationship is approved by business experts before AI agents use it.