Context and control for people and agents alike
Enterprise-grade governance. Child's-play complexity.
Let’s hear it for BI. No, seriously. It got your boss to look at it every morning. Numbers people trust, shown only to those who need them, and…wait a minute…you’re pasting that CSV into ChatGPT!? What about the context, governed definitions and access controls. Those were the good bits!
Solution
The confidence you need to deploy analytics agents at scale
Count Metrics, our semantic layer, gives agents the definitions, documentation, and guardrails they need to produce accurate, consistent work, with everything version-controlled and easy to maintain.
AI that shows its working
Unlike most AI you've used, Count doesn't hide away its thinking. Every agent's conversation persists and is visible to all, and every cell it creates is, well, just another cell in the canvas. You can view, audit, approve, and even edit SQL, or change no-code visuals and tables.
The real modern data stack
Count Metrics lets you control the data that is passed to agents by the compute layer, and enrich it with context either from its own model or ingested from third-party semantic layers. At the same time, canvases and reporting are locked against user permissions ensuring that the right people see the right data.
The end of “I think this is right”
Agent context control
Determine exactly what data and context the agent works with.
Coming soonSemantic layer syncing
Reference and extend metric definitions from LookML, Snowflake Cortex and others for use in Count.
Enterprise permissions
SSO, SCIM, data residency, and everything else your compliance team expects.