offdataai
Ontology builder

Turn your data model into a business ontology

offdataai derives concepts, relations and metrics from your tables, lets your team review every AI suggestion, and publishes the result as a standard OWL ontology that people, tools and AI agents can all use.

  • From $1/month
  • 8 SQL targets
  • 174 templates
FreshCart ontologyDraft
placescontainssold atCustomer↳ dim_customerOrder↳ fct_orderProduct↳ dim_productStore↳ dim_storeMETRICNet revenue = sum(net_amount)
AI suggestion · Needs review
Published · OWL / JSON-LD
Concepts are drafted from your model and stay bound to their tables; every AI suggestion waits for review.
Watch the demo

See it in action

A narrated walkthrough, recorded in the real app.

How it works

Three steps, minutes not months

1

Describe or import

Answer a short interview, open a template, draw on the canvas or connect a live database.

2

Review a validated model

Keys, grain, history and PII are checked before any code is written. Refine it in plain English.

3

Ship and keep it current

Native DDL, dbt, seeds, docs and an ontology. Push to Git, diff versions, generate migrations.

Overview

Why teams choose offdataai

app.offdataai.com
An ontology drafted from a grocery model, with every suggestion awaiting review

An ontology drafted from a grocery model, with every suggestion awaiting review

  1. 01

    Most warehouses are full of names that only their authors understand.

  2. 02

    An ontology is the layer that says what those tables mean: which business concepts exist, how they relate, and how metrics such as revenue are calculated.

  3. 03

    Without it, every analyst, dashboard and AI agent has to rediscover that meaning on its own, and they rarely agree.

  4. 04

    offdataai builds the ontology from the model you already have, whether it came from the AI interview, a template, the Model Builder or a live database.

  5. 05

    You can also start blank and import a model later, or import an OWL file you already have.

  6. 06

    Concepts stay bound to their tables, so when the model changes the ontology can be re-derived instead of rewritten by hand.

  7. 07

    When it is ready, publish it so its IRIs resolve, export it as OWL, ask it questions in plain English, or let AI agents query it through the built-in MCP server.

Real output

The code it writes, not a sketch

This is the shape of what offdataai generates here, straight from the validated model. Copy it, download it, or push it to Git.

  • Derived from your model, not from scratch
  • Human review for every AI suggestion
  • Published, resolvable IRIs
sales.ttlowl · turtle
1@prefix : <https://app.offdataai.com/ontology/acme/sales#> .
2@prefix owl: <http://www.w3.org/2002/07/owl#> .
3@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
4@prefix skos: <http://www.w3.org/2004/02/skos/core#> .
5
6:Customer a owl:Class ;
7 skos:prefLabel "Customer" ;
8 skos:definition "A person or company that has
9 placed at least one order." .
10
11:Order a owl:Class ;
12 skos:prefLabel "Order" .
13
14:placedBy a owl:ObjectProperty,
15 owl:FunctionalProperty ;
16 rdfs:domain :Order ;
17 rdfs:range :Customer .
Capabilities

What the ontology builder does

  • Derived from your model, not from scratch

    Concepts, relations and metrics come straight from the data model, with bridge tables folded into relations and every concept bound to its source tables.

  • Human review for every AI suggestion

    AI-proposed concepts, relations and renames wait in a review queue. “Improve names” cleans up labels like fct_ord_ln in one pass, for you to approve.

  • Published, resolvable IRIs

    Publish and the ontology and each concept, relation and metric get links that work: a readable page for people, Turtle, RDF/XML or JSON-LD for machines, via content negotiation.

  • Standard exports and imports

    Download OWL as Turtle, JSON-LD or RDF/XML, or the raw JSON. Open it in Protégé or load it into a knowledge graph, and import OWL files from other tools.

  • Several sources, one vocabulary

    Combine a warehouse model with a live operational database. The same Customer in both becomes one concept with two bindings.

  • Ready for AI agents

    Agents connected over MCP or the API can search concepts, find join paths and ask questions in plain English, under the access rules and masking you set.

0

Validated templates

0

SQL targets

0

Modeling paradigms

0+

Industries covered

Generates native SQL and dbt for 8 platforms · connects live to Snowflake, Databricks, BigQuery, Redshift and Postgres

SnowflakeBigQueryDatabricksRedshiftPostgreSQLSynapseFabricDuckDBdbtSnowflakeBigQueryDatabricksRedshiftPostgreSQLSynapseFabricDuckDBdbt
FAQ

Frequently asked questions

What is a data ontology, and how is it different from a schema?
A schema describes storage: tables, columns and keys such as fct_ord_ln.amt. An ontology describes meaning: the business concepts (Customer, Order Line), how they relate (an Order contains Products), and the metrics built on them (Revenue). offdataai keeps both in sync because the ontology is derived from, and bound to, the same data model.
How does offdataai build the ontology?
First a deterministic pass derives concepts, relations and metrics from the structure of your model, with no AI and no credits. It strips modeling prefixes like dim_ and fct_, turns bridge tables into many-to-many relations instead of fake concepts, and keeps a binding from every concept to its tables. An optional AI pass then improves names and writes business definitions.
Do AI suggestions change the ontology automatically?
No. Every AI-proposed concept, relation or rename goes into a review queue. A person accepts, edits or rejects it, so the published ontology only contains what your team has approved.
Can one ontology cover several databases?
Yes. You can add several sources, such as a project's data model and a live database read by the Database Modeler, to one ontology. The same business concept in two systems becomes one concept with two bindings.
Can I start an ontology before I have a model?
Yes. Start a blank ontology and add concepts by hand. When a model is ready, the Built on control imports a project, a database read by the Database Modeler or a model drawn in the Model Builder, and merges it into the working copy. Review decisions you already made stay as they are.
What does publishing do?
Publishing makes the ontology's IRIs resolve: the ontology itself and each concept, relation and metric. A person who opens the link sees a readable page with the definition; an RDF tool asking for Turtle, RDF/XML or JSON-LD gets the machine-readable form. Unpublished ontologies stay private and are only reachable with an API key.
Which export formats are supported?
OWL in Turtle, JSON-LD and RDF/XML, plus the raw JSON document. The RDF formats open in tools such as Protégé and can be validated with SHACL.
Can I import an ontology I already have?
Yes. Upload an OWL file in Turtle, RDF/XML, JSON-LD or N-Triples (up to 5 MB) and offdataai creates a new ontology from it. An offdataai export comes back field for field. From other tools it brings classes, object and datatype properties, labels, comments and subclassing, and lists anything it skipped. The new ontology gets your own IRIs, and owl:imports links are not followed.
Which plan includes the ontology builder?
Building, versioning, publishing and exporting ontologies start on the Starter plan. The AI enrichment pass (better names and definitions), live connections for answering questions from your data, and the API and MCP server for agents start on Pro. Each plain-English question uses one AI credit.
Can people and agents ask the ontology questions?
Yes. Ask in plain English and offdataai plans the question from the ontology's metrics and fields, never free SQL, runs it against the bound databases and answers in a sentence with the rows and the SQL that ran. Agents ask the same way through the ask_ontology MCP tool or POST /api/v1/ontologies/{id}/ask. For agents, the ontology's access rules and row filters apply, and personal data stays masked unless the API key has pii:read.

Part of the offdataai platform

The business context behind accurate AI answers, built from the data model up.

See all six stages →
  1. 01DesignLogical, physical and dimensional models.
  2. 02GenerateSQL, dbt, documentation and migrations.
  3. 03DefineBusiness metrics, semantic models and ontology.
  4. 04ConnectReal warehouse schemas and metadata.
  5. 05GovernDrift, impact analysis, tests and approvals.
  6. 06ActivateMake trusted context available to AI agents.

This page covers Define. Every stage works on the same model, so what you design here carries through to the rest.

Accuracy starts with context

Give your AI agents context they can trust.

Design the model, define what your metrics mean, and serve that context to every agent and BI tool, on the warehouse you already run.

Book a demoGet started

Self-serve plans available