Process documents
Bring in policies, procedures and data dictionaries. Kenseme reads them and proposes the terms they depend on.
Platform
One description of your business, from documents to answers
Kenseme captures what your business means, models it as an ontology in open standards, binds it to your data, governs it, and puts it to work in the data agent or the agent you already run. Five areas, one model running through all of them.
01 · Document meaning
Capture the vocabulary from the sources you trust
Most of what your business means is already written down, scattered across policies, procedures, data dictionaries and glossaries. Kenseme reads those sources and turns them into defined, sourced terms.
Extract glossary terms
Each proposed term arrives with a definition and the source it came from, ready for your experts to review.
Industry standards
Anchor your vocabulary to FIBO, GS1, HL7 FHIR or IEC CIM instead of starting from scratch.
02 · Infer the business model
Build the ontology your agents reason over
An ontology is a formal description of your business: the concepts, how they relate, and the rules between them. Kenseme builds one in W3C OWL 2 from your glossary, your documents and your industry standard.
Generate with AI
Draft an ontology from your glossary, documents and chosen industry standard in one pass.
Refine in conversation
Describe the change you want in plain language, add a concept, split one in two, explain a relationship, and Kenseme proposes the edit.
See the whole model
The diagram view shows every concept and relationship, so reviewers can spot what's missing.
Open and exportable
Written in W3C OWL 2. Export all of it whenever you like.
Industry schema repository
Start from proven structures for your industry rather than a blank canvas.
Versioned
Every change lands in a version history you can review.
03 · Bind to the data
Tie every concept to the data that holds it
Bind the ontology to your warehouse or lakehouse, and design the data that doesn't exist yet. Every run shows a preview first, so nothing changes without someone seeing it.
Bind to your data
Map concepts and properties to tables and columns in a database connection or a Fabric Lakehouse.
Publish to Microsoft Fabric
Publish the bound ontology to Fabric, then push or pull changes, with a preview before every run.
Design data models
Create, version and deploy data models, including AI-generated star schemas.
Generate code
SQL with procedures for SQL Server, Azure SQL, Fabric Warehouse, Postgres, MySQL, Redshift and Snowflake. PySpark notebooks for Databricks and Fabric Lakehouse.
Build pipelines
Generate the pipelines that bring data into the model, in your platform's own dialect.
Column-level lineage
Trace any business term to the columns behind it.
Binding works with database connections and Fabric Lakehouse. Code generation covers all eight platforms listed above.
04 · Govern
Governance that travels with the model
Definitions, owners, versions and lineage live with the model itself, not in a separate spreadsheet. When the catalog needs them, publish them to Microsoft Purview.
Business glossary
One place for every governed term, its definition and where it came from.
Custom attributes
Add owner, steward, review cycle or any field your governance model uses.
Version history
See what changed in a model, and when.
Roles
Give each person the access their role needs.
Publish to Microsoft Purview
Publish your glossary and model to Purview, and run it again whenever you need to.
Lineage
Column-level lineage connects each governed term to the data behind it.
05 · Operate and analyze
Put the description to work
Ask the data agent a business question and get an answer you can check, or publish the model into the agent you already run.
Ask the data agent
Ask a business question in plain language. The data agent runs it against your bound data.
See how it got there
Every answer comes back with a grid, a chart and the exact SQL, so anyone can check it.
Saved reports
Save the questions you ask often and come back to them.
MCP access
Expose the ontology over MCP so other agents and tools can read it.
Your agent, grounded
Already running an agent? Publish the model into it instead.
AI where it helps
AI drafts and suggests throughout. Your people make the calls.
See it on your own data
Together we pick one domain, the one where a wrong answer costs the most. Two weeks later you can ask a real question and check the answer.