The meaning of your data comes from your business.

The foundation AI needs is a precise understanding of what your data means to the people who run the business. We capture it from the people who make the decisions, in their own words, and keep it as rules anyone can read and check.

Try it on your business ↓ Start free

Try it Tell it about your business in a few sentences, and it builds the model with you.

What the demo shows

The demo needs JavaScript. In words, it goes like this:

You tell it about a business in a few sentences, like “a dental practice, four dentists, we bill per treatment”.
Each thing you mention becomes a rule you can read, drawn as you go.
Say what you want to measure and the same rules are arranged into a star schema.
Ask a question and the answer comes back with every figure behind it.

The business here is a sample, so you can try it without handing over any data.

Starmaker

The people who make the decisions, and the person who knows the database.

The model is the part of a foundation that fails, and everything else is built on top of it. So we build it with the people who know what the data means.

1 · Your words

They say what they measure

In their own words, the way they talk about the business.

2 · Your data

Each word is traced to your data

The person who knows the database shows where each one comes from, whether it is stored or worked out from other values.

3 · Your star

Built and checked

The star is loaded and tested against your rows, and it is ready for reports and AI the same day.

Each product belongs to exactly one subcategory.

The foundation stays open to the business. Every decision is a sentence like this one that they can read and say yes or no to, and every report and every AI answer follows it.

For the data team

A complete platform around the model.

Your warehouse and pipelines keep doing the work they do well. GramSpec adds what the data means, decided by the business and kept where your team can manage it.

Connects to SQL Server, PostgreSQL, MySQL, MariaDB, Snowflake and Databricks, or a CSV upload.
Imports the structure of a live database or a Power BI template.
Keeps every version of the model, with a diff and a restore.
Names a steward for each table.
Restricts rows for each person who can see a board.
Runs read-only, with encrypted credentials, two-factor sign-in and a log of every query.
Answers and investigates on the same rules, in Vision and Reason.
Hands the model to your own agents and apps through an API and MCP.

Read the specification API reference The research paper (PDF)

Build the foundation from what your business knows.

Bring the people who make the decisions and the person who knows your database.

Start free Sign in Read the spec