Home / ekai for Snowflake

A native app, built for Snowflake from the ground up.

ekai is the systems of intelligence layer between your data and your AI agents. It is available as a Snowflake Native App, listed on the Snowflake Marketplace. Profiling, modeling and validation run inside your own account under your governance, and verified models publish to Snowflake semantic views and Cortex Agents.

Book a demo View on Snowflake Marketplace

How does ekai work inside your Snowflake account?

Three steps, from install to a verified answer in Cortex.

Runs in your account

ekai runs as a Snowflake Native App in your own Snowflake account. Discovery reads your tables read-only.

Your experts answer in plain words

ekai profiles your tables in place, then asks the people who know what each number means. Their answer becomes the definition.

Publish to Cortex

Every definition is checked against your data warehouse, then published as Cortex Analyst semantic views for Cortex Analyst, Cortex Agents and Snowflake CoWork.

See every step of how ekai works

Why run ekai inside Snowflake? Four reasons it fits the way you already work.

Raw rows stay in your account

Your raw rows never leave your Snowflake environment. ekai works from metadata and statistical summaries.

Cortex and Snowflake CoWork ready

Publish governed semantic models as Cortex Analyst semantic views, so the same verified definitions power Cortex Analyst, Cortex Agents and Snowflake CoWork.

Snowflake Native App

A Snowflake Native App that runs in your own Snowflake account.

Native security and governance

Runs under your roles, your data warehouses, your access policies, and works with Snowflake's own security and governance.

Illustrations · demo data

Does it work, and is it safe?

Customer result6 hours, $56

Secunetics built its production dbt pipeline with ekai in 6 hours for $56, against 96+ hours and about $26,400 by hand.

See the customer results Security

Built for your security review

Discovery reads your tables in place, and your raw rows never leave your data warehouse. ekai's SOC 2 Type II audit found zero exceptions.

See architecture and security

ekai across the Snowflake ecosystem.

Pitch nights, spotlight features and the Data Cloud Summit: ekai and Snowflake building together.

Mo Aidrus pitching ekai at Snowflake Startup Pitch Night

EventLinkedIn

Snowflake Startup Pitch Night, Menlo Park

AI adoption requires semantically modeled data and business context for sophisticated AI deployments to work.

Read on LinkedIn

FeatureSnowflake blog

Snowflake Startup Spotlight: ekai

Snowflake highlights how ekai applies agentic AI to accelerate enterprise data work and deliver faster outcomes.

Read on Snowflake blog

Semantics › Sales and revenueOwner: FN

Model DetailsBusiness RequirementsAI ModelingData TransformationCode Sync

EXPLORERAI Modeling 6Business GlossaryLineageSales and Revenue Semantic Model ReviewData CatalogMetricsData Validation

Data Validation

Each rule has its validation logic in SQL and an expected result. The Data Transformation agent runs the rules when it builds.

GRAINone row per ORDER_IDExpected result0 violations

REFERENTIALevery REGION_CODE exists in REF.REGIONSExpected result0 violations

MEASUREAMOUNT - TAX - DISCOUNT >= 0Expected result0 violations

TEMPORALORDER_DATE falls inside the fiscal quarterExpected result0 violations

MEASUREnet_revenue >= 0 on every orderExpected result0 violations

← Business RequirementsData Transformation →

Illustration · demo dataArticleMedium

Leveraging Agents for Semantic Modeling with ekai

How ekai uses agentic AI to automate semantic modeling and turn raw data into intelligent business context.

Read on Medium

The ekai team at the Snowflake AI Data Cloud for Startups booth

EventLinkedIn

Snowflake Data Cloud Conference

Conversations around semantic layers, data products, governance, and building the right data strategy.

Read on LinkedIn

Common questions

Last updated October 28, 2026

What is ekai?

ekai is the systems of intelligence layer between your data and your AI agents. ekai learns what your data means by asking the experts who know it, proves every definition against your data warehouse, and publishes it with their name on it, so a data product goes from an idea to production in hours, not months.

Does ekai work with Snowflake Cortex Analyst?

Yes. ekai publishes governed semantic models as Cortex Analyst semantic views, so Cortex Analyst, Cortex Agents and Snowflake CoWork answer from the definitions your experts authored and ekai checked against your data warehouse.

How do I install ekai in Snowflake?

ekai is a Snowflake Native App, listed on the Snowflake Marketplace. It runs in your own account, and setup needs ACCOUNTADMIN. ekai is also available as ekai SaaS or self-hosted.

What permissions does ekai need in Snowflake?

Discovery needs read access. To build semantic models, the Data Transformation agent needs write access to create its own ekai schema, separate from your source tables, where it builds staging views and mart tables. ekai never edits your source tables, and it runs under your roles, your data warehouses and your access policies.

Does my data leave Snowflake?

Your raw rows never leave your Snowflake environment. ekai works from metadata and statistical summaries, and the privacy policy sets out what can be shared with the AI providers you use.