How we built a personal data scientist for every Notion employee

Summary

Notion built Data Scout, an internal data agent connecting Snowflake and Notion, letting employees query governed data in plain language and cutting request turnaround from days to minutes. Within two months, weekly data team requests fell by about 80 percent, and roughly half of all employees now use it. The agent enforces Snowflake permissions per user and uses Notion business context, enabling teams such as Sales, Engineering, and Customer Experience to ask questions about account adoption, onboarding drop-off, or support volume using shared definitions. Using MCP, teams built Data Scout Reporter for scheduled reports and domain-specific agents that reuse the same context. Notion learned correct SQL could still answer the wrong question due to four failure modes, so they built governed access, curated context, instructions, query tracing, and a review process where change evidence is not approval.

Takeaways

1. 1

   Data Scout reduced weekly data team requests by about 80% within two months and is used by roughly half of Notion employees.

2. 2

   Even SQL that runs correctly can answer the wrong question due to four failure modes: wrong meaning, routing, measurement, or interpretation.

3. 3

   Reliable data agents depend on governed access, curated context, and clear instructions, plus query tracing and a validation process where evidence of a change is not approval until verified by owners.

FAQ