The question layer running in your cloud, with a read-only role.
| Region | Revenue | Customers |
|---|---|---|
| North America | $4,812,300 | 1,204 |
| Europe | $3,206,950 | 988 |
| Asia Pacific | $1,944,120 | 612 |
| Latin America | $702,480 | 231 |
Text to SQL
Plain questions are answered from your approved metrics, never from a guess, with the query shown.
| Region | Revenue | Customers |
|---|---|---|
| North America | $4,812,300 | 1,204 |
| Europe | $3,206,950 | 988 |
| Asia Pacific | $1,944,120 | 612 |
| Latin America | $702,480 | 231 |
When people try a chat tool instead, it makes up its own definition of revenue, and two answers to the same question disagree.
of decision makers do not fully trust the data they rely on.
Sourceprecisely.com
of business leaders are not sure the data they need is accessible.
Sourcesalesforce.com
of their data is untrustworthy, say data and analytics leaders.
Sourcesalesforce.com
Anyone can ask the data and get the number finance agrees with.
| What changes | Without it | With it |
|---|---|---|
| Waiting | Days in the analyst queue. | An answer in a minute. |
| Definitions | Each dashboard has its own. | One agreed metric for everyone. |
| Trust | No way to check the number. | The query shown with every answer. |
What changes for your teams. We pick the tools to fit the systems you already run.
| Region | Revenue | Customers |
|---|---|---|
| North America | $4,812,300 | 1,204 |
| Europe | $3,206,950 | 988 |
| Asia Pacific | $1,944,120 | 612 |
| Latin America | $702,480 | 231 |
| Region | Revenue | Customers |
|---|---|---|
| North America | $4,812,300 | 1,204 |
| Europe | $3,206,950 | 988 |
| Asia Pacific | $1,944,120 | 612 |
| Latin America | $702,480 | 231 |
Illustrative figures, not a client result. Your own baseline is taken in the first week.
Another company built the same kind of system and wrote publicly about how it went.
What they learned
Plain questions get usable queries when the system knows your tables and shows the query it wrote.
Uber’s data platform handles about 1.2 million interactive queries each month.
You own the config, the tests and the runbooks, so you can swap any part later.
| Region | Revenue | Customers |
|---|---|---|
| North America | $4,812,300 | 1,204 |
| Europe | $3,206,950 | 988 |
| Asia Pacific | $1,944,120 | 612 |
| Latin America | $702,480 | 231 |
Typical building blocks: dbt Semantic Layer and dbt MCP, or Cube; an agentic SQL fallback with schema pruning, dry run and self-repair; a read-only role; a golden question set in CI.
Alternatives: WrenAI; Snowflake Cortex Analyst; Databricks Genie (Vanna is archived).
The work happens in your cloud, with the people who will own it.
Plain questions answered from agreed metrics.
About 5 weeks. You get a price range before the call and one fixed number after it. That number is the invoice.
We pick the one that fits the systems you already run. You own the config, the tests and the runbooks, so you can swap any part later. Most often the dbt Semantic Layer with dbt MCP, or Cube; WrenAI, Snowflake Cortex Analyst or Databricks Genie when they fit better.
No. It runs with a read-only role, and each query is checked with a dry run before it runs.
It says so, writes a draft query and sends it to an analyst. It does not guess a definition.
The common cloud warehouses, through the semantic layer you already have or one we set up with you.
Your data team writes real questions with known answers. Every change must pass them.
Plain questions answered from agreed metrics. You own the config, the tests and the runbooks.