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
See it in action
A narrated walkthrough, recorded in the real app.
Three steps, minutes not months
Describe or import
Answer a short interview, open a template, draw on the canvas or connect a live database.
Review a validated model
Keys, grain, history and PII are checked before any code is written. Refine it in plain English.
Ship and keep it current
Native DDL, dbt, seeds, docs and an ontology. Push to Git, diff versions, generate migrations.
Why teams choose offdataai

An ontology drafted from a grocery model, with every suggestion awaiting review
- 01
Most warehouses are full of names that only their authors understand.
- 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.
- 03
Without it, every analyst, dashboard and AI agent has to rediscover that meaning on its own, and they rarely agree.
- 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.
- 05
You can also start blank and import a model later, or import an OWL file you already have.
- 06
Concepts stay bound to their tables, so when the model changes the ontology can be re-derived instead of rewritten by hand.
- 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.
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
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#> .56:Customer a owl:Class ;7 skos:prefLabel "Customer" ;8 skos:definition "A person or company that has9 placed at least one order." .1011:Order a owl:Class ;12 skos:prefLabel "Order" .1314:placedBy a owl:ObjectProperty,15 owl:FunctionalProperty ;16 rdfs:domain :Order ;17 rdfs:range :Customer .
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
FabricDuckDB
FabricDuckDBFrequently asked questions
What is a data ontology, and how is it different from a schema?
How does offdataai build the ontology?
Do AI suggestions change the ontology automatically?
Can one ontology cover several databases?
Can I start an ontology before I have a model?
What does publishing do?
Which export formats are supported?
Can I import an ontology I already have?
Which plan includes the ontology builder?
Can people and agents ask the ontology questions?
Explore offdataai
- AI Data ArchitectHire Atlas by the hour: voice or text, 43 languages, read-only.
- Semantic layerGoverned metrics, compiled to SQL for people and AI agents.
- Context layer for AI agentsConcepts, metrics, join paths and docs for agents over MCP.
- Data catalogEvery table and column, which concepts use it, where it's copied.
- Data modeling tools comparedDesktop, diagram, code-first and AI-native tools side by side.
- MCP server for AI agentsGive Claude and other agents your tables, joins and metrics.
Part of the offdataai platform
The business context behind accurate AI answers, built from the data model up.
- 01DesignLogical, physical and dimensional models.
- 02GenerateSQL, dbt, documentation and migrations.
- 03DefineBusiness metrics, semantic models and ontology.
- 04ConnectReal warehouse schemas and metadata.
- 05GovernDrift, impact analysis, tests and approvals.
- 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.
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.
