# Ontology Building

> Source: https://ibl.ai/ontology

Map your organization's world into a living knowledge graph that powers every AI agent.

## The Concept — What Is an Organizational Ontology?

A structured representation of your organization that AI agents can reason over.

### The Semantic Layer

The nouns — what exists in your world:

- **Entity types** model real-world things — students, courses, departments, equipment
- **Attributes** capture characteristics — enrollment date, grade level, capacity
- **Relationships** define how entities connect — a student enrolls in a course, a course belongs to a department

### The Operational Layer

The verbs — what can happen in your world:

- **Actions** define permissible changes — enroll a student, update a grade, approve a request
- **Functions** encode logic — calculate GPA, assess risk scores, route approvals
- **Permissions** govern who can do what — role-based access at every level

Together, these layers form a digital twin of your organization — a complete, navigable map that AI agents use to understand context, make decisions, and take action.

## The Why — Why Build an Ontology?

Five principles that make ontology-driven AI fundamentally different:

1. **Shared understanding at scale** — Every team, department, and agent operates from the same definitions. New data sources are modeled into a common language. Local decisions gain global context.
2. **Human-readable by design** — Users interact with familiar terms, not tables and joins. The ontology bridges technical and non-technical teams.
3. **Build once, reuse everywhere** — A well-modeled entity type serves every downstream application. The cost of launching the tenth agent is a fraction of launching the first.
4. **Capture decisions as data** — Every action taken through the ontology is recorded and available. One user's insight becomes another user's input.
5. **Ground AI in organizational reality** — Models and agents operate on the same structured knowledge that humans use. Decisions feed back into the ontology for continuous improvement.

## Building Blocks — Core Ontology Types

- **Entity Types** — Schema definitions of real-world objects or events (e.g. Student, Course, Department)
- **Attributes** — Characteristics that describe an entity (e.g. Name, enrollment date, GPA)
- **Relationships** — Typed connections between entities (e.g. Student enrolls in Course)
- **Actions** — Controlled operations that create, modify, or remove entities in a single transaction (e.g. Enroll student, approve request)

## Advanced Modeling — Extending the Ontology

- **Interfaces** — Abstract shapes that multiple entity types can implement for uniform agent interaction
- **Functions** — Code-based logic for derived metrics, complex validations, and model inference
- **Derived Attributes** — Values calculated at runtime by traversing relationships and aggregating data
- **Structured Attributes** — Composite attributes grouping related fields (e.g. Address with street, city, postal code)
- **Semantic Search** — AI-powered search matching by meaning rather than exact keywords

## Governance — Permissions & Security

- **Schema Permissions** — Control access to type definitions
- **Data Permissions** — Control access to individual records with row-level and field-level security

Agents inherit the same permissions as the users they serve — no special access, no backdoors.

## AI Agents — From Ontology to Operational Agents

- **Discovery** — Agents navigate the graph to find the right information
- **Analysis** — Agents compute insights across entities and relationships
- **Automation** — Agents execute actions within governed boundaries
- **Learning** — Agent decisions feed back into the ontology as new data

## Best Practices

1. **Start with what people already call things** — Use familiar terms, not system jargon
2. **Model for decisions, not just storage** — Every type should support a real decision
3. **Let the ontology grow with usage** — Start focused, extend organically
4. **Treat actions as first-class citizens** — Define operations with clear rules from the beginning

## Getting Started

1. **Identify core entities** — Map the real-world objects that drive key decisions
2. **Define relationships** — Draw the connections agents will need to traverse
3. **Model actions and permissions** — Specify what can change, who can change it, and what happens
4. **Deploy your first agent** — Launch an agent that operates on the ontology

---

*[View on ibl.ai](https://ibl.ai/ontology)*