The universal semantic layer for ai
If it’s not AtScale, it’s just a guess.
AtScale is a universal semantic layer with a built-in AI Computation Engine (ACE). It computes your metrics for AI agents and BI tools, so they don’t write their own SQL, and it returns the same result to every agent, analyst and app. Define a metric once, and every tool uses that definition.
Ask a model for a number and it writes SQL against whatever tables it can see. Ask again tomorrow and it may write different SQL and get a different answer. Every attempt also scans your warehouse again, so the same problem gives you wrong answers and a bigger compute bill.
It happens in real companies. At Blue Yonder, an AI agent gave the chief transformation officer the wrong bookings number, with no test plan behind it. On the BIRD-Interact benchmark, a frontier model working alone got about half of real business questions right
AtScale sits between your data and every agent, analyst and app that asks it a question.
Snowflake
Databricks
Google BigQuery
Microsoft Fabric
Data Warehouse
Ontologies Catalog
Spark
Ontologies
Data Catalogs
Metadata
Claude
Cursor
Chat GPT
Copilot
Codex
Power BI
Tableau
Excel
01
Turns metrics into SQL. Computes in place
02
Build and maintain semantic models using AI.
New
03
Navigate prompts to one metric. Ask when unsure.
New
04
Inherited access control. Enforced once.
New
05
Scores answers against a gold standard.
AI
BI
Semantic model
Prompt
Clarify
Answer
Serve
AtScale sits between your data and every agent, analyst and app that asks it a question.
The AI Computation Engine computes complex metrics in your data platform the same way every time.
Fixes complex metrics
Runs multi-pass and time-series calculations directly in your data platform
Keeps the aggregates it builds so repeat questions cost less
Works out which metric a question means before anything runs.
Fixes vague prompts
Asks a clarifying question when it isn’t sure what was meant
Handles questions from AI agents the same way it handles people’s
Builds and maintains your semantic model with AI.
Fixes vague semantics and bad data
Picks the right columns, defines each business term and sets how to compute it
Cleans up messy values, and your data engineers review and approve every change
Coming
Measures accuracy by running your own business questions.
Fixes unmeasured accuracy
Checks each answer against known-correct results
Sends every failure back to CoModel to fix
Coming
Applies your existing warehouse permissions in one place.
Fixes scattered access rules
Enforces the same permissions for every agent, analyst and app
Versions, reviews and rolls back metric definitions like code
The full platform, on any warehouse. Snowflake, Databricks, BigQuery, Redshift, Azure.
Runs natively inside Snowflake, and it’s the engine inside Semantic Views. Links out to the sub-site.
Use any data platform, BI tool or AI agent, and change any of them later without redefining a single metric.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
Lorem ipsum dolor sit amet consectetur adipiscing elit occaecat eos duis minim est cupidatat voluptatum non veniam et ut non ut cupidatat minim deleniti dolores lorem nisi qui laboris corrupti qui eos est irure molestias ducimus ullamco ullamco duis autem ducimus sunt est imperdiet et odio ullamco tempore pariatur sed.
