# AI Workbench: Ontology driven data modelling toolkit preview

DevFeed: [AI Workbench: Ontology driven data modelling toolkit preview](<https://devfeed.tech/articles/ai-workbench-ontology-driven-data-modelling-toolkit-preview-80362.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/ontology-toolkit-preview>)

Author: Hiba Jamal

Published: 2026-03-24T00:00:00Z

Content type: release

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>)

Tags: [data-modelling](<https://devfeed.tech/tags/data-modelling.md>), [ontology](<https://devfeed.tech/tags/ontology.md>), [product](<https://devfeed.tech/tags/product.md>)

## AI overview

The dltHub AI Workbench transformation toolkit uses source annotations, taxonomy and business ontology to generate a canonical data model. The preview explains how explicit entity definitions and business rules can guide LLMs when integrating disparate systems, then provides installation commands and the annotate-sources entry point.

## Source excerpt

How are LLMs supposed to know the business logic of how you use Hubspot, Luma and Slack together? How are they supposed to know what a customer means to you?