Question 17

A data team is curating an AI/BI Genie Space over a Unity Catalog `sales` schema so that business users can ask natural-language questions and receive accurate, trusted answers. Genie behaves nondeterministically, so the team wants to maximize the chance of correct, verifiable SQL while following Databricks' recommended curation practices. Which **three** actions should the team take to improve the Genie Space's accuracy and data discovery? (Choose THREE.)

• AAdd clear, descriptive table and column comments in Unity Catalog (and, where helpful, space-level descriptions and column synonyms) so Genie understands what each field represents.
• BAdd example SQL queries — using the most typical phrasing of each user question as the title — so Genie can match prompts to verified queries and learn to answer related questions.
• CRegister parameterized example queries and Unity Catalog SQL functions as trusted assets so that responses generated from them are labeled **Trusted**.
• DReplace all table and column comments with a single large free-text instruction block, because Genie relies only on plain-text instructions and ignores Unity Catalog metadata.
• EGrant every business user the `MANAGE` privilege on the underlying catalog so Genie can rewrite the source tables at query time.
• FMaximize accuracy by adding as many text instructions as possible, even when they overlap or conflict, so Genie always has more guidance to choose from.