Question 20
An analytics engineering team reports this behavior: A support team needs to categorize short ticket descriptions and expects a standard SQL aggregation to understand their meaning semantically. Which test outcome is the strongest acceptance evidence?
Explanation
Correct Answer
This verifies cortex text classification use because semantic classification requires an appropriate AI capability rather than ordinary numeric aggregation. The corresponding corrective action is: Evaluate a supported Snowflake Cortex AI function for the classification task under governance. A green status for a different component would not independently establish this result.
Incorrect Answers
Application sharing requires governed Snowflake object and role access, not account administration. “Build a Streamlit in Snowflake app with scoped data permissions and the supported runtime” would address that alternative cause, not the condition in this question: semantic classification requires an appropriate AI capability rather than ordinary numeric aggregation.
“Push suitable transformations into Snowpark and materialize only the necessary result” responds to this separate finding: snowpark transformations are generally represented as operations executed in Snowflake compute. This question instead needs “Evaluate a supported Snowflake Cortex AI function for the classification task under governance”, so the alternative does not meet the stated condition.
Document content extraction needs a supported unstructured-data processing capability. “Use governed file access and appropriate document AI or text-extraction functions for the workload” applies to that separate problem. The observed case is a support team needs to categorize short ticket descriptions and expects a standard SQL aggregation to understand their meaning semantically; choosing this alternative would address the wrong failure mode.