Intercept.
The question arrives in plain language, from an AI assistant or from an agent over MCP, before it reaches any query engine.
AtScale ava (Ask, verify, answer)
Prompt disambiguation for AI.
Research shows that two out of five questions people put to enterprise data systems are ambiguous, so the first step toward 100% AI accuracy is to disambiguate those prompts.
Ava disambiguates vague prompts from people and AI agents. It sits between the prompt and AtScale ACE, the AI Computation Engine, and resolves each one to a single metric in your semantic model before ACE computes anything.
THE PROBLEM
“What was our revenue in Q3?”
doesn’t have one answer.
It could mean bookings, recognized revenue, ARR, TCV or net sales, and each is a different number.
Every one of those metrics is correct for someone. Finance closes the books on recognized revenue, sales runs on bookings, and the board watches ARR. Hand an LLM that ambiguity and it’ll pick one without asking which you meant or telling you which it chose.
The answer looks right, but it answers a question you didn’t ask.
how ava works
Ava asks which revenue you meant.
When a question could mean more than one thing, Ava shows you the matching metrics and asks which one you mean before ACE calculates the answer. That choice can then be approved into the semantic model, so the next user gets the right answer automatically.
Ava demo video — coming soon
Resolves the question before anything gets computed
WHAT IT DOES
Resolves the question
Every request is matched to one metric definition and its dimensions before anything is computed.
Asks when it can't tell
Better to ask which revenue than to return the wrong one. A clarifying question costs a second.
Works with any client
Ava sits between the AI and ACE, outside any one vendor’s tool, so Claude, Codex and Cursor all get the same treatment.
Intercept, resolve, hand off
Resolve.
Ava matches it to one metric and its dimensions in the semantic model. When more than one metric fits, it asks.
Hand off.
ACE computes that metric in your warehouse, and the answer comes back with the name of the metric that produced it.
FOR AGENTS
Agents get the same resolution, automatically.
An agent can’t stop and ask a person which revenue it means. Through the AtScale MCP server, it finds metrics by their business descriptions and applies the rules your team’s already approved through Ava. It calls one metric by name, and ACE computes it.
the proof
How a clarifying question fixes a
BIRD-Interact answer.
On BIRD-Interact, the public benchmark, a user prompts for “a ranked list of stars in the galaxy.” Without AtScale, the model guesses alphabetical, then size, and runs out of budget. With AtScale, Ava asks which ranking the user means, and a single query gets it right. Across the benchmark, adding an AtScale semantic layer made an LLM twice as accurate, and most of that lift came from asking before computing.
Ava gets the question right, and ACE gets the math right.
See how Ava fits with the rest of AtScale →
Ava workflow video — coming soon
Why this isn’t text-to-SQL
The questions engineers ask first
Is this text-to-SQL?
No. Ava resolves a question to one defined metric, and ACE, the AI Computation Engine, computes it. Text-to-SQL has a model write a new query against raw tables for each question.
What happens when Ava can't tell?
It asks which metric you meant before ACE computes anything. A clarifying question takes a few seconds, and a wrong number can cost far more.
Does it work with my agent?
Yes. It works with any client that supports remote MCP servers, including Claude, ChatGPT, Google Gemini, Databricks agents, Codex, Cursor and agents you build yourself. Agents sign in with OAuth, and your access rules apply to them the same way they apply to people.
FAQs
Is this text-to-SQL?
No. Ava resolves a question to one defined metric, and ACE, the AI Computation Engine, computes it. Text-to-SQL has a model write a new query against raw tables for each question.
What makes a question ambiguous to Ava?
It’s ambiguous when more than one metric in the semantic model matches the word someone used. “Revenue” can match bookings, recognized revenue, ARR, TCV and net sales. Ava lists every metric that fits and asks which one you’re after.
What happens when Ava can't tell?
It asks which metric you meant before ACE computes anything. A clarifying question takes a few seconds, and a wrong number can cost far more.
Can I see which metric Ava picked?
Yes. The answer comes back with the name of the metric that produced it, so a person or an agent can see exactly what’s been computed.
Does Ava remember my answer?
Yes, once your team approves it. Each clarification goes back to Semantic Modeling, where your team decides whether it becomes a rule. Approved rules apply to every person and agent after that.