# Agentic Ontology — The Knowledge Layer Every AI Agent Reasons Over

> Source: https://ibl.ai/product/agentic-ontology/financial-services

The knowledge layer a bank's or insurer's AI agents reason over: accounts, transactions, alerts and loans from core banking, the policy system and the warehouse, queryable in place over MCP with every access logged. On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

**The knowledge layer your agents reason over**

**1.6M+** Platform Users · **400+** Organizations · Trusted by Syracuse University, SUNY, Google, NVIDIA, Microsoft, OpenAI and Kaplan.

> “ibl.ai does amazing work and are great people.” — Paul LeBlanc, former President and CEO, Southern New Hampshire University

Don’t take our word for it? [See what our partners say](https://ibl.ai/case-studies)

[Scope a deployment](https://ibl.ai/contact) · [See what's inside](https://ibl.ai#built-with) · [Book a Demo](https://cal.com/iblai/30min) · [Contact Us](https://ibl.ai/contact)

Want to read the source? [View the code on GitHub](https://github.com/iblai/ontology)

## Two ways to run it

### We host it: Start at $0 on the ibl.ai cloud

Free tier with renewable monthly credits, no credit card, usage-based from there. Move to your own infrastructure anytime, nothing to rebuild.

[Hosted deployment](https://ibl.ai/hosted-deployment) · [See pricing](https://ibl.ai/pricing)

### You own it: Take the whole codebase

Backend and infrastructure under a perpetual license, so you own all the code and the data. Your cloud, on-premise or air-gapped, under your control.

[Full code license](https://ibl.ai/full-code-license)

## Available on

- **Web** — Any modern browser, nothing to install ([details](https://ibl.ai/download#platforms))
- **Chrome** — Side-panel extension: your agents on any page ([details](https://ibl.ai/download#platforms))
- **macOS** — Universal desktop app, signed and notarized ([details](https://ibl.ai/download#platforms))
- **Windows** — Desktop installer for x64 and ARM64 ([details](https://ibl.ai/download#platforms))
- **iOS** — iPhone and iPad on the App Store ([details](https://ibl.ai/download#platforms))
- **Android** — Phones and tablets on Google Play ([details](https://ibl.ai/download#platforms))
- **Linux** — Build from source on GitHub ([details](https://ibl.ai/download#platforms))

## What makes it agentic

Not a data warehouse and not a RAG index. A map of your organization's nouns and verbs that agents reason over, built on the systems you already run, queried in place over MCP — with the data, the cache and the permissions staying inside your network.

- **[No data extraction](https://github.com/iblai/ontology)** — Databases and SaaS apps are exposed as MCP tools where they live; the layer is itself one MCP server behind your firewall and identity provider. No VPN to a vendor cloud, no third party holding your data. (MIT · github.com/iblai/ontology)
- **[Nouns and verbs, not tables](https://ibl.ai#how-it-fits)** — Entity types, attributes and relationships for what exists; actions, functions and permissions for what can happen. Agents read the same reality your people do, in the terms they already use. (Semantic + operational layers)
- **[Every agent compounds](https://ibl.ai/service/ai-transformation)** — Model an entity once and every agent inherits it, with the user's own role enforced on every query. This is the layer an AI Transformation engagement delivers first. (Delivered by AI Transformation)

## How is Agentic Ontology different from a managed vendor's knowledge layer?

Managed AI vendors extract your data through a VPN into their cloud and rent you access to a map of your own organization. Agentic Ontology keeps the map in your network, open source, and yours.

| | Agentic Ontology | A managed knowledge layer |
|---|---|---|
| **Where the data goes** | Stays in your network, queried in place over MCP. | Extracted into the vendor's cloud. |
| **Who holds the map** | You do: open source (MIT), self-hosted. | The vendor; you rent access. |
| **Identity** | Your identity provider, the user's own role on every request. | The vendor's accounts and service keys. |
| **Models and runtimes** | Any LLM, any authorized MCP client; switch anytime. | The vendor's models. |
| **Pricing** | Usage or a flat license; no per-seat or per-connector fee. | Per seat, per connector, per year. |
| **Exit** | The layer keeps running after the contract. | The map leaves with the vendor. |

## Why ibl.ai

- **Your Code. Your Data.** — Full ownership, zero vendor lock-in ([more](https://ibl.ai/full-code-license))
- **Any LLM, Your Choice** — Air-gapped or any cloud provider’s ([more](https://ibl.ai/self-hosted-ai))
- **85% Lower Cost** — Significantly cheaper at scale ([more](https://ibl.ai/ai-cost-calculator))
- **Engineers Included** — Our team builds it with yours ([more](https://ibl.ai/service/ai-transformation))

Agentic Ontology by ibl.ai is the map of a regulated firm that its AI agents reason over: accounts, transactions, alerts, loans, households and the relationships between them, with the actions an agent may take and the permissions it inherits.

It connects core banking, the policy system, the CRM and the warehouse in place over MCP, read-only and role-scoped through your identity provider, behind your own firewall, with every access logged.

Open source, self-hosted, and yours — including full code access.

## What This Is

### 

A unified knowledge layer that runs inside your network. It makes the systems you already run — SIS and ERP databases, data warehouses, SaaS apps — queryable by AI agents over MCP, with the data, the cache and the permissions staying on-premise.

### MCP in, MCP out

Databases are exposed as MCP tools through Google's MCP Toolbox; REST systems get lightweight MCP servers. The layer is itself one MCP server behind your firewall and identity provider, so any authorized runtime — ibl.ai, Claude, Cursor, your own app — connects and gets results scoped to the caller's role.

### Model once, every agent inherits it

Model an entity once and every agent inherits it: the tenth agent costs a fraction of the first, because the knowledge, the definitions and the governance are already there.

## The semantic layer: the nouns, what exists in your world

### Entity types

Model real-world things in the terms financial services already uses: accounts, transactions, alerts, loans.

### Attributes

Capture characteristics — enrollment date, grade level, capacity — with a type that defines the shape and a value on each instance.

### Relationships

Typed connections that carry meaning — a student enrolls in a course, a course belongs to a department — one-to-one, one-to-many or many-to-many.

## The operational layer: the verbs, what can happen in your world

### Actions

Permissible changes with validation rules and side effects: triage an alert, score a loan, file a report.

### Functions

Logic that reads attributes, traverses relationships and returns computed results — calculate a GPA, assess a risk score, route an approval.

### Permissions

Who can do what, at every level, inherited from the roles your identity provider already holds.

### Result

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

## Your ontology, in financial services's own terms

### The primitives are the same everywhere

Entity types, attributes, relationships and actions. What changes is the vocabulary, and the ontology is modeled in the terms your people already use.

### Nouns

Accounts, transactions, alerts, loans.

### Verbs

Triage an alert, score a loan, file a report.

### Systems

Connected in place over MCP: core banking, the policy system, the CRM and the warehouse.

## Why do AI agents need an ontology?

### Shared understanding at scale

Every team, department and agent operates from the same definitions — no conflicting spreadsheets, no siloed dashboards. New sources are modeled into a common language rather than spawning another disconnected view.

### Human-readable by design

People interact with familiar terms, not tables, joins or API endpoints. Domain experts explore data directly without writing queries or waiting on engineering.

### Build once, reuse everywhere

A well-modeled entity type serves every downstream application — dashboards, agents, reports, integrations. The cost of launching the tenth agent is a fraction of launching the first.

### Capture decisions as data

Every action taken through the ontology — an approval, a classification, an override — is recorded. Audit trails and decision history are built in, not bolted on.

### Ground AI in organizational reality

Agents fail first because data is siloed across the SIS, LMS, CRM, ERP and warehouse. An agent grounded in a unified ontology reads the same reality your people do — no translation layer where hallucinations creep in.

## What are the building blocks of an ontology?

### Entity types

Schema definitions of real-world objects or events; each has instances. e.g. Student, Course, Department, Device, Transaction.

### Attributes

An attribute type defines the shape (text, number, date, location); an attribute value is the data on a specific instance. e.g. name, enrollment date, capacity, GPA.

### Relationships

Typed connections between entities that carry meaning, including links between entities of the same type. e.g. Student enrolls in Course, Manager supervises Employee.

### Actions

Controlled operations that create, modify or remove entities and relationships in one transaction, enforcing validation rules and triggering side effects such as notifications.

### Interfaces, functions and derived attributes

Abstract shapes shared by several entity types; code-based logic agents call at decision time; values computed live from the graph — a department's average satisfaction, a student's total credits.

### Semantic search

Text converted to vector embeddings and matched by meaning, so agents find the right entities even when a query matches no exact field value.

## How is the knowledge layer governed?

### Schema permissions

Who can view or modify entity type definitions, create relationship types, or define and edit action types.

### Data permissions

Who can read specific instances and execute actions on which entities, with row-level and field-level security for sensitive data.

### Agents inherit, never bypass

Agents inherit the same permissions as the people they serve — no special access, no backdoors. Every request forwards the user's own identity token; the layer never stores a credential of its own.

### Read-only by construction

Discovery runs a read-only safety suite first — seven write attempts that must all be denied — before a source is introspected and provisioned.

## How does an ontology become 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, so the operational record enables retraining, pattern detection and continuously improving recommendations.

### Every agent benefits from every improvement

When a new entity type or relationship is added, every agent that touches that domain gains it immediately. The investment compounds.

## How do you build an ontology for your organization?

### Start with the nouns

Model entity types, attributes and relationships in the business terms your domain experts already use: accounts, transactions, alerts, loans.

### Then add the verbs

Actions with validation rules, functions that encode logic, and permissions inherited from your existing roles. Connect source systems once over MCP, and govern everything read-only and role-scoped from day one.

### Ship it from the CLI

The whole lifecycle ships from a CLI — service discovery, schema analysis, role validation, scheduled sync and deployment — with built-in defaults for 22 common enterprise and higher-education systems, including core banking, the policy system, the CRM and the warehouse.

### Let it grow with usage

Start with a focused set of entity types for your first use cases, model for the decisions people actually make, and treat actions as first-class citizens from the beginning.

## Why Agentic Ontology instead of a managed vendor's knowledge layer?

### Where the data goes

Agentic Ontology: Stays in your network, queried in place over MCP | Managed vendor: Extracted through a VPN into the vendor's cloud

### Who holds the map

Agentic Ontology: You do — open source, MIT, self-hosted | Managed vendor: You rent access to a map of your own organization

### Identity

Agentic Ontology: Your identity provider, role-scoped per request | Managed vendor: The vendor's accounts and service keys

### Models

Agentic Ontology: Any LLM, any authorized runtime, switch anytime | Managed vendor: The vendor's models

### Pricing

Agentic Ontology: Usage or flat license, no per-seat fee | Managed vendor: Per seat, per connector, per year

### Exit

Agentic Ontology: The layer keeps running after the contract | Managed vendor: The map leaves with the vendor

## Part of the ibl.ai platform

### 

Agentic Ontology is what an AI Transformation engagement delivers first: ibl.ai's forward-deployed engineers model your nouns and verbs, connect your systems over MCP and hand you the layer. Agentic OS runs the agents that reason over it; Agentic SIS, LMS, CRM and Wallet are the records it connects. One sign-in, one set of roles, one platform you own.

## Experience Agentic Ontology Today

### Run It Yourself

Clone github.com/iblai/ontology (MIT, Python 3.11+), run `ontology config init`, and add your first source

### Scope a Deployment

Contact ibl.ai to model your ontology with forward-deployed engineers inside your network

### Schedule a Demo

See agents reason over a real ontology, in your sector's terms

## Run Agentic Ontology on your own terms

*Bring us a hard problem. Keep the code.*

Start free on our cloud today, or take the whole codebase into your own infrastructure. Either way our engineers work alongside your team, and you own all the code and the data.

[Scope a deployment](https://ibl.ai/contact) · [Book a 30-minute demo](https://cal.com/iblai/30min) · [See what's inside](https://ibl.ai#built-with)

ibl.ai is family-owned and operated from New York, NY — a U.S.-headquartered, domestically-owned long-term partner, not a vendor that sells licenses and moves on. · SOC 2 Type II certified

---

*[View on ibl.ai](https://ibl.ai/product/agentic-ontology/financial-services)*