Proof of concept

Two weeks. One domain. Your data.

We start every engagement the same way: a short proof of concept on your own data. Together we pick one domain, the one where a wrong answer costs the most, and prove it out end to end. Not a demo on someone else's data. Yours.

How the two weeks run

Pick it, describe it, ask it

Pick the domain

We agree on one domain and the questions that matter in it, and gather the documents, glossaries and people who know it best.

Describe and bind

We draft the description from your sources, refine it with your experts, and bind it to your live data.

Ask real questions

Your team asks the questions they actually need answered, in the data agent or the agent you already run, and checks every answer against the SQL.

What we ask of you

  • One domain, and a sponsor who cares about getting it right
  • The documents that describe it: policies, glossaries, data dictionaries
  • Read access to the data that holds it, in a database or a Fabric Lakehouse
  • A few hours from the people who know the domain best

What you leave with

  • A described domain in W3C OWL 2 that you own and can export
  • That description bound to your live data
  • A data agent answering real questions, with the SQL behind every answer
  • A clear view of what the next domain would take

Common questions

Why one domain?

Because one domain done properly tells you more than ten done roughly. It shows what the description looks like, how your data binds to it, and whether the answers hold up, on a problem your team already cares about.

Do we need Microsoft Fabric?

No. Kenseme binds to a database connection or a Fabric Lakehouse, and generates code for eight platforms, including Snowflake and Databricks.

Where does Kenseme run?

Kenseme is a hosted service, run by Macula Systems.

What happens after two weeks?

You decide. Extend the description to the next domain, or take it with you. It is written in an open standard and it's yours either way.

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.