Home / Workflows

Discovery and Semantics run as one governed path.

Discovery profiles your data in place and builds a reviewed entity model. Semantics turns it into verified semantic models, code, tests and docs.

Book a demo

Discovery › Sales warehouseOwner: FN

Connection DetailsOnboardingSchema & Relationships

SALES.ORDERSORDER_IDnumberCUSTOMER_IDnumberORDER_DATEdateAMOUNTnumberTAXnumberDISCOUNTnumberREGION_CODEtext

SALES.ORDER_ITEMSORDER_ITEM_IDnumberORDER_IDnumberSKUtextQUANTITYnumberUNIT_PRICEnumberUNIT_COSTnumberLINE_AMOUNTnumber

CRM.CUSTOMERSCUSTOMER_IDnumberCUSTOMER_NAMEtextSEGMENTtextREGION_CODEtextCREATED_ATdate

REF.REGIONSREGION_CODEtextREGION_NAMEtextSTATEtextROLLUPtext

REF.FISCAL_CALENDARFISCAL_DATEdateCAL_DATEdateFISCAL_QTRtextFISCAL_YEARnumber

Schema Agent

Joined ORDER_ITEMS to ORDERS on ORDER_ID with a FULL OUTER. An inner join would silently drop orders with no line items.

AMOUNT does not declare gross or net. Noted for business requirements.

Keys · Relationships · Documentation · Entity relationship (DBML)

← OnboardingSemantics →

ekai product · demo data

Learn your data where it sits.

Read-only profiling, with your experts filling the gaps.

See how Discovery works

Ship models your business trusts.

dbt code, tests and docs as one unit, checked inside your warehouse.

See how Semantics works

Illustrations · demo data

Publishes to

Snowflake semantic views and Cortex Agents

Databricks Genie

dbt project in your own Git

Discovery

Automated discovery and entity modeling. Steps 1 to 3: connect, model the structure and the architecture plan.

What you get

Data profile
Onboarding Document (Source Onboarding Summary)
Keys, relationships and documentation
Entity relationship diagram (DBML)

Discovery›Sales warehouseConnection Details

Snowflake5 tables linked · 2 context files · Modified 20 Oct 2026

View Connection Parameters

TablesLink the tables you choose

SALES.ORDERS
SALES.ORDER_ITEMS
CRM.CUSTOMERS
REF.REGIONS
REF.FISCAL_CALENDAR

Data Profile5 tables and 27 columns profiledView Profile

ekai product · demo data

Step 1 · Connect

Connect and link your tables, then profile them in place.

Step 2 · Model the structure

The Onboarding Agent asks about your domain and writes the Source Onboarding Summary.

Step 3 · Architecture plan

The Schema Agent maps keys and relationships, and you review the ERD.

Semantics

Automated semantic modeling and code generation. Steps 4 to 6: generate, verify and publish.

What you get

Business requirements document
Business glossary, lineage, data catalog, metrics and data validation
dbt project in your Git
Published to Snowflake semantic views and Cortex Agents, Databricks Genie, BigQuery data agents, or dbt MetricFlow for Postgres and Redshift

Semantics›Sales and revenueBusiness Requirements · AI Modeling

Business Requirements agentDoes net revenue include tax and discounts?Exclude both · answered by Finance

Business Glossary
Lineage
Sales and Revenue Semantic Model Review
Data Catalog
Metrics
Data Validation

SourceStagingMarts

ORDERSstg_ordersfct_net_revenue

CUSTOMERSstg_customersdim_customer

REGIONSstg_regionsdim_region

net_revenueMetrics · on fct_net_revenue

SUM(amount − tax − discount)

Illustration · demo data

Step 4 · Generate

The Business Requirements agent captures requirements with your expert, then the AI Modeling Agent writes the glossary, lineage, catalog, metrics and validation rules.

Step 5 · Verify

The Data Transformation agent builds the models and runs the tests, and an independent ekai reviewing agent audits the result.

Step 6 · Publish

You approve the Data Transformation agent's publish checkpoint, and Code Sync pushes the project to your Git.

Common questions

Last updated October 28, 2026

How does ekai profile the data in my warehouse?

Read-only, and in place. ekai connects to your warehouse with read access, profiles the tables you link and maps their keys and relationships. Your raw rows stay in your warehouse and ekai never edits your source tables.

What is the Discovery workflow?

Discovery is the first of ekai's two workflows. It connects to your warehouse, profiles your data in place, asks your experts about anything the data cannot explain, and produces a reviewed entity model: keys, relationships, documentation and an entity relationship diagram.

What is the Semantics workflow?

Semantics is ekai's second workflow. It turns your experts' answers into a semantic model, then generates the dbt code, tests and documentation, checks every definition against your warehouse, and publishes the approved model to your AI agents.

How long does it take ekai to build a semantic model?

A full Discovery and Semantics run on one domain takes about 4 to 6 hours, against months of manual data and context engineering.

Does ekai need my experts to write code?

No. ekai asks your experts plain questions about what the data means. Your data engineers review the generated dbt code and tests instead of writing them from scratch.

Where do ekai's semantic models get published?

To Snowflake semantic views and Cortex Agents, Databricks Genie and BigQuery data agents, or to dbt MetricFlow for Postgres and Redshift. The dbt project goes to your own Git.