Bring your business intent into Snowflake.
AI in Snowflake can only be as right as its understanding of your business. Duodata captures what your numbers mean — with an owner your business names — and puts that meaning to work in Semantic Views, so Cortex Analyst answers the question your business is actually asking.
AI can give you a confident answer to the wrong business question.
Cortex Analyst reads tables and columns. It doesn't know which revenue your finance team reports, who owns that definition, or which adjustments it includes — unless someone tells it.
From business meaning to platform execution
Defined by the business
Net revenue
= gross revenue − discounts − credits
- Owner
- Finance
- Used for
- Quarterly reporting
Duodata model
Your business meaning, ready for AI
One agreed definition with an owner, a time grain and the words people use to ask for it.
Choose your platform
Your platform executes the calculation. Pick one; you don't need both.
Answer in Cortex Analyst
Net revenue grew 5.4% from Q2 to Q3.
Definition used: net revenue = gross revenue − discounts − credits (owner: Finance), served through Semantic Views.
Fictional example
Same data. Different question. Different decision.
Two quarters of fictional revenue show what changes when AI uses the definition your finance team signs off.
Question
“How much did revenue grow?”
AI answer without the business definition
Revenue grew 10%.
Gross revenue: $10.0m → $11.0m. The gross-revenue answer is 4.6 percentage points above the growth Finance reports.
Gross revenue, Q2 vs Q3 2026
Growth: 10.0%
| Component | Q2 | Q3 |
|---|---|---|
| Gross revenue | $10.0m | $11.0m |
| Discounts | $0.5m | $0.8m |
| Credits | $0.2m | $0.4m |
| Net revenue | $9.3m | $9.8m |
Fictional example in USD. Not customer data.
Business owners define intent. Your data team owns the platform.
Business owners
- Agree what each measure means, in plain language.
- Name the owner and where it is used.
- Review changes before AI uses them.
Your data team in Snowflake
- Maps definitions to tables, columns and relationships.
- Deploys native semantic views through its own release process.
- Keeps governance, access and runtime in Snowflake.
Snowflake Semantic Views hold logical tables, facts, dimensions and metrics inside Snowflake, and Cortex Analyst uses them to answer questions. Duodata helps your business and engineering teams curate the definitions, ownership and mappings behind those semantic views.
Existing reports and models are valuable inputs: we start from what your teams already use.
Semantics, deployed and maintained for you.
The Snowflake Native App is how the agreed definitions reach Snowflake: it produces the Snowflake semantic views used by Cortex Analyst, and keeps them in step when definitions or schemas change.
The layers behind the answer, built with your team.
Definitions alone don't move data. Our engineers work alongside yours to build the transformations, facts and dimensions the agreed measures need — and to prove the output matches the source.
- 01
Silver and gold layers
Transformations, facts and dimensions built to your standards.
- 02
Maintained formulas
Definitions and schema changes flow through review, not rework.
- 03
Reconciliation
Source → silver → gold → semantic checks on every change.
Worked examples for Snowflake
- Food production & quality“Which inspection results actually count as passed?”Why one pass-rate question produced two confident answers — and how the quality team's agreed definition became the one AI uses.For quality and operations teams · Quality · Operations · FinanceSee the Food production & quality story
- Air cargo“How much of what we booked actually flew?”How a cargo team agreed what 'booked actually flew' means — cohort, cutoff and weight — so planning and AI work from the same number.For cargo operations and commercial teams · Cargo operations · Commercial planning · FinanceSee the Air cargo story
Official Snowflake documentation
- Snowflake Semantic Views(opens in a new tab)
- Cortex Analyst(opens in a new tab)
- Snowflake Native Apps(opens in a new tab)
Running on Databricks? See Duodata for Databricks
Start a free pilot
Bring one business question, its owner, the data in Snowflake and the result you expect. We agree the scope of a free pilot together before we start.
- 01One business question
- 02One owner of the definition
- 03The data it depends on
- 04A review on your platform
- Start a free pilotWatch demo