A data engineering team is deploying Snowflake Cortex Analyst to enable natural language queries over their structured SALES_DATA table, which includes columns like PRODUCT_CATEGORY, SALES_AMOUNT, and ORDER_DATE. To maximize the accuracy and trustworthiness of responses for business users, which of the following practices should the team implement when configuring their semantic model?

Correct Answer: A,E
Option A is correct because semantic models are defined in YAML and uploaded to a stage. When using VQR, logical table names in the SQL field must be prefixed with two underscores (e.g., sales_data), and logical column names are used directly. Option B is incorrect because 'Explore options' is a component of Cortex Agents for planning and disambiguation, not a feature within Cortex Analyst's semantic model configuration. Cortex Analyst uses semantic models to bridge language gaps but does not have an explicit 'Explore options' feature in this context. Option C is incorrect because VQR SQL queries must use the *logical* table and column names defined in the semantic model, not the physical names of the underlying dataset directly. Option D is incorrect. While exists, its purpose is to present a full set of predefined questions for onboarding, not to force prioritization for *all* complex questions regardless of semantic similarity to the user's input. This could lead to incorrect answers if the question isn't truly an onboarding question. Option E is correct because Cortex Analyst can integrate with Cortex Search Service within dimension definitions of the semantic model to improve literal string searches, which helps in cases where literal values cannot be directly extracted from the question.