Athena drafts dimensions, measures, and business objects from your raw catalog and a paragraph of context—reviewable, versioned, and enforced across every query.
A Fortune 500 retailer drafted their semantic model from three sentences
Agents and business users have to see the same data or the answers drift. Without an agreed definition of "net sales," the dashboard, the analyst, and the agent will each be right and all disagree.
Everyone knows the semantic model is essential. Nobody wants to build it. So it lives in someone's head and a dozen Measure files.
Should cost a paragraph, not a quarter.
Inspect the catalog. Point Athena at Snowflake, Databricks, BigQuery, or the Lakehouse. It reads tables, columns, and existing lineage.
Add context. A paragraph in business language. Regions, brands, plants, matters, whatever your world is made of.
Draft. Dimensions, measures, calculations, and joins, each with the reasoning shown. Legacy tables without foreign keys get a proposed join key and a flag.
Review. Accept, edit, or ask why, like a document. Version it.
Serve. Dashboards, =ATHENAQUERY cells, notebooks, and agents query through the model with each user's own warehouse permissions. Semantic model first; SQL second.
Semantic models. Shared definitions of your measures, dimensions, and joins, plus business entities like a brand, plant, or deal. Drafted from your catalog and a few sentences.
| Capability | People can | Agents can | Together |
|---|---|---|---|
| Semantic models | Describe the business; review and edit the draft like a document. | Draft definitions from the catalog; flag joins it cannot confirm. | Dashboards and agents give the same answer to the same question. |
Anything a person can do here, an agent can do with the same permissions, and both land in the same audit trail.
A data lead at a Fortune 500 retailer typed three sentences about their business. Athena inspected the raw warehouse catalog and drafted the dimensions, measures, and calculations. The reaction in the room: "That's the power of AI and LLMs today."
A CPG provider's product lines lived in different systems. As typed objects in one ontology, the same question works across both.
Size, owner, client, industry as typed objects, evolved from years of historical deal data in Databricks. The agent proposes new properties as it reads more.
Clients, matters, people, and documents as objects with governed, reversible actions. Conflicts checks and knowledge management queries run against the same graph.
Object types carry actions with policies. An agent can propose "mark Purchase Order as disputed"; a human approves; the action is versioned and reversible.
Every object type exposes a versioned API. Applications and external systems consume the same definitions the dashboards do.
“Lets us get a lot more out of our data than [...] We can sit on top of all of the data in [our data warehouse] as opposed to just, like, our little ingested, you know, three gigabytes semantic models. I think we have a lot of power here.”
“This is where the puck's going and this is where the moat is for an enterprise.”
“So you gave her three sentences. And she spit out that.”
“It's good to understand the capability of the platform. That how far, and how quickly you guys can get these things going [...] that has been impressive overall.”
“Gave Athena the spreadsheet, explained which column I was trying to figure out, and then ten secs it told me... exactly how the calculation was based on the other data.”
“He wrote the entire stuff. By itself. And I was there, and I was thinking, alright. If I had to write all this stuff, I mean, I would've spent days, days, days.”
“I send that to the programmer and he said, alright. I read your file. I copied the section of the code because he has the right interface, and it works. Wow. Just like magic.”
“One workspace. All different, let's say, avatars of their output data. Right? Suddenly, it's dashboard. Excel is here. PowerPoint is when it's all together. It's very impressive.”
“Use the Athena platform probably closer to the concept and how it was designed, like, with the spaces architecture where you've got a set of primitives and capabilities, and you bring together the right set of capabilities to solve a task.”
“Digital worker, it gets spun up, it gets given access to the toolkits that it needs. It gets given access to the data that it needs. Just exists for the period it needs to exist to perform the task. And then it gets torn back down again afterwards.”
Verbatim from customer calls. Customers anonymized.
Every query through the model runs with the user's own warehouse permissions; agents included.
Definitions are versioned; changes attributed; rollbacks available.
Object actions are policy-gated and reversible.
The model is yours. Export it.
The first draft is a draft. Legacy tables without foreign keys need a human to confirm join keys. Athena shows its reasoning for each proposal so the review is quick.
A single definition of your business metrics, so every report and every agent answer agrees.
Athena drafts it from your existing data in minutes; your analysts review and approve it.
Owners approve every change before it goes live.
Records every change by a person or an agent, rolls back one contributor's edits without losing anyone else's, and keeps the model, instructions, and sources behind each agent action.
How the platform is deployed: Athena's managed cloud, your cloud on AWS, GCP, or Azure, on-prem, air-gapped, or GovCloud. Same platform in every option.
Build, Work, and Data on top; 150+ connectors and every surface in and out; one map of the whole platform.
We will draft the model in front of you and let your data lead argue with it.