Model
The metric is defined once, in SML, the open modeling language behind Apache Ossie.
THE CALCULATOR FOR ENTERPRISE AI
How does AtScale ACE keep AI answers accurate?
AtScale ACE (AI Computation Engine) compiles your semantic model into a graph, plans computations, and runs it to compute each answer inside your data platform. Repeat questions hit aggregates that ACE maintains and optimizes for performance and cost.
THE PROBLEM
LLMs are probabilistic. ACE is deterministic.
ACE is the SQL calculator for enterprise AI.
Ask an LLM for recognized revenue and it has to pick the contracts, spread them over service periods, convert currencies, and roll up by region and quarter. It writes new SQL every time, and the number looks plausible even when it’s wrong. ACE computes it from one definition, so you’ll get the same answer every time.
How ace works
AtScale ACE: The AI Computation Engine
With your metric definitions built into the engine, ACE compiles each question into SQL, rolling revenue up a hierarchy, computing year-to-date and rolling windows, and reporting inventory as a closing balance. It learns from the queries people run, builds aggregates, and caches repeat answers, so it gets faster and cheaper the more it’s used.
ATSCALE ACE : THE AI COMPUTATION ENGINE
SEMANTIC DEFINITIONS
Revenue
Churn
Inventory
Gross margin
On-time delivery
Same-store sales
Net interest margin
Basket size
conversion rate
Loss ratio
Readmission rate
Days of cover
Average order value
…
COMPUTATION – atscale ace
SQL Generation
Turns a metric request into the query your warehouse runs.
Aggregates
Built from the queries people actually run, so ACE gets faster on its own.
Caching
Repeat questions come back without touching the warehouse again.
Multidimensional
Hierarchies, drill paths and roll-ups a flat table can’t express.
Time series
Period-over-period, year-to-date and rolling windows, computed the same way every time.
computes in place, on the platform you already run
Snowflake
Databricks
Amazon Redshift
Apache Iceberg
Microsoft Fabric
Google BigQuery
for agents
How AI agents call ACE
AI clients and agents reach ACE through the AtScale MCP server, where Ava resolves each request to one certified metric. The LLM picks the metric and ACE computes it, planning the joins, grain and passes from the semantic graph, then running the SQL inside your data platform. Every answer is logged with the exact SQL behind it, so you’ll know how each number was built.
Model, compute, optimize
Compute
ACE turns the request into SQL and computes it inside your warehouse. Your data never moves, and the same certified number goes back to whatever asked for it, over XMLA, SQL, REST or MCP.
Optimize
We optimize the SQL so you don’t have to. Aggregates form from the queries people actually run, so the same metric keeps getting faster without anyone predicting the questions.
AtScale makes LLMs twice as accurate.
On BIRD-Interact, the public benchmark built from realistic enterprise questions, adding AtScale made an LLM twice as accurate in preliminary runs. Ava confirms what each question means, and ACE computes the answer. An agent exploring a schema on its own runs query after query and still guesses. An agent that calls ACE asks for the metric by name and gets one result back, often from an aggregate or a cached answer. Across thousands of questions a day, that’s a real saving in warehouse compute and tokens.
Blue Yonder: 800 tables became ten semantic models in ACE.
Computes wherever your data already lives
FAQs
Is this text-to-SQL?
No. ACE computes a defined metric from its rules, the same way every time. Text-to-SQL has a model write a new query against raw tables for each question.
Does my data move?
No. ACE computes every metric on your data platform, where the data already lives.
Which data platforms does ACE run on?
Snowflake, Databricks, Google BigQuery, Amazon Redshift, PostgreSQL and InterSystems IRIS. Self-hosted AtScale also runs on Microsoft SQL Server, Azure SQL, Azure Synapse, Cloudera CDP and IBM Db2. ACE writes SQL in each platform’s own dialect.
Can I see the SQL? Can I change it?
Yes to both. Every answer traces back to the metric definition and the exact SQL that produced it. Your data engineers can change how a metric is defined and tune how it’s computed. CoModel, coming this fall, will suggest changes from real query history, and a data engineer will decide what ships.
Does ACE work with BI tools too?
Yes. Power BI and Excel query it live over XMLA and DAX, Tableau and Looker over SQL, Google Sheets through the AtScale Connector add-on, and Python notebooks through AI-Link. Every tool gets the same number.
Which AI agents can call ACE?
Claude, ChatGPT, Google Gemini, Databricks agents and any client that supports remote MCP servers, through the AtScale MCP server. An agent requests a metric by name with run_query and pulls the exact SQL with get_outbound_queries. The tools are read-only and agents sign in with OAuth.
What about speed and cost?
ACE gets faster and cheaper with use. It builds aggregates from the queries people run and caches repeat answers, so many answers don’t need a full table scan.
Do I buy ACE separately?
No. It’s part of AtScale, alongside Ava, the MCP server, Semantic Modeling and Governance.