Ontology

The ontology is Humm’s map of your business. It defines the key entities in your world—like Customers, Accounts, and Products—and how they relate to each other. A well-defined ontology helps Humm understand your questions and return accurate answers.

​

What’s in the Ontology?

​

Entities

Entities are the core concepts in your business. Common examples:

• Account — A company or organization you do business with
• Contact — A person associated with an account
• Opportunity — A potential deal or sale
• Subscription — A recurring revenue relationship
• User — Someone who uses your product
• Event — An action or activity in your product

Each entity has attributes (like name, created date, or status) that describe it.

​

Relationships

Relationships define how entities connect:

• Accounts have Contacts
• Accounts have Subscriptions
• Users belong to Accounts
• Users generate Events
• Opportunities convert to Subscriptions

These relationships let Humm navigate your data and answer questions that span multiple systems.

​

Metrics

Metrics are the key performance indicators you track:

• Monthly Recurring Revenue (MRR) — Revenue from subscriptions
• Churn Rate — Percentage of customers who cancel
• Net Promoter Score (NPS) — Customer satisfaction measure
• Health Score — Overall account health indicator

Humm uses metric definitions to calculate values consistently across your analyses.

​

How Humm Builds the Ontology

When you connect integrations, Humm automatically discovers your data structure:

1. Schema discovery — Humm reads your tables, fields, and data types
2. Entity detection — Humm identifies business entities from your data
3. Relationship inference — Humm detects how entities connect based on keys and patterns
4. Metric recognition — Humm identifies common metrics and calculations

This automatic process gives you a working ontology immediately. You can then refine it to match exactly how your team thinks about the business.

​

Viewing the Ontology

Click Ontology in the sidebar to explore Humm’s understanding of your business. You’ll see:

• Entity list — All recognized entities and their attributes
• Relationship map — Visual diagram of how entities connect
• Metric definitions — How key metrics are calculated
• Data sources — Which integrations power each entity

​

Refining the Ontology

The automatic ontology is a starting point. Refine it to improve accuracy:

​

Renaming Entities

If Humm calls something “Company” but your team says “Account,” rename it. Humm will understand both terms, but using your team’s language makes conversations more natural.

​

Adding Relationships

If Humm missed a connection between entities, add it manually. For example, if your product data links to accounts through a custom field, define that relationship so Humm can traverse it.

​

Defining Metrics

Add your specific metric calculations. If your health score formula is unique to your business, define it in the ontology so Humm calculates it correctly every time.

​

Adding Business Context

Enrich entities with descriptions and examples:

• “Churned accounts are those with status = ‘cancelled’ and no active subscription”
• “Enterprise tier includes Pro, Business, and Enterprise plans”

This context helps Humm interpret your questions accurately.

​

Ontology and Accuracy

The ontology directly affects answer quality: Investing time in your ontology pays off in every conversation.

​

Tips for a Better Ontology