Databricks-DA-Assoc Developing AI/BI Genie Spaces — All Questions With Answers

Question 1

A data analyst is setting up an AI/BI Genie Space for the marketing team. They want to provide example questions that users can ask to get started. Which TWO of the following are valid ways to add example questions to a Genie Space? (Choose two.)

Accepted Answer

In the Genie Space configuration, go to the Instructions tab and add sample questions.. Example questions can be added through the Instructions tab in the Genie Space configuration. This tab provides a dedicated area for sample questions, which are displayed to users and used to guide the model. Using the Instructions tab is the standard method, while other options such as API endpoints or SQL comments are not valid for this purpose.

Answer

Use the Databricks REST API to POST a list of questions to the Genie Space's /examples endpoint.

Answer

Add the questions as comments in the SQL query editor of the Genie Space.

Answer

In the Genie Space configuration, go to the Data tab and add the questions as table descriptions.

Question 2

A retail analytics team is building an AI/BI Genie space over a Unity Catalog table named `sales_transactions`. Business users frequently ask questions such as 'What were the top 10 products by revenue last month?' The team wants Genie to consistently interpret 'revenue' as `sum(quantity * unit_price)` and to return results quickly. They have already added a sample question. Which action should they take next to improve Genie's accuracy and performance for these recurring questions?

Accepted Answer

Create a Databricks SQL materialized view that pre-aggregates daily product revenue, then add it to the Genie space as a trusted table.. Curated, pre-aggregated assets added as trusted tables give Genie explicit column semantics and faster scans. By exposing a revenue column already computed as quantity times unit_price, the space no longer has to infer the formula from raw fields, which directly fixes the recurring misinterpretation. This approach also reduces the data volume scanned for common monthly product questions, improving response time.

Answer

Add a comment to every column in `sales_transactions` describing its business meaning.

Answer

Increase the SQL warehouse cluster size attached to the Genie space so queries return faster.

Answer

Grant the business users SELECT privileges directly on `sales_transactions` so Genie can read the raw data.

Question 3

A data analyst is configuring an AI/BI Genie Space that includes a table with a column named `rev`. The analyst wants Genie to understand that `rev` means total revenue in USD. The analyst also wants to ensure that when users ask for revenue, Genie uses this column. Which action is most effective?

Accepted Answer

Rename the column to `total_revenue_usd` and add a column comment explaining it is total revenue in USD.. Genie relies heavily on column names and comments to interpret user questions. Renaming `rev` to `total_revenue_usd` and adding a descriptive comment provides unambiguous metadata that directly maps to the business term, making it the most effective single action.

Answer

Add a metric view that calculates total revenue from `rev` and include it in the Genie Space.

Answer

Create a view that aliases `rev` as `total_revenue_usd` and add the view to the Genie Space.

Answer

Add an instruction in the Genie Space: "rev means total revenue in USD."

Question 4

A data analyst is configuring an AI/BI Genie space for a sales team. The team wants Genie to answer questions about a Unity Catalog table named `main.sales.orders`. The analyst has already selected the table in the Genie space setup. What is the next required step before business users can start asking questions in the space?

Accepted Answer

Publish the Genie space and share it with the appropriate users or groups.. A Genie space becomes usable by the target audience only after it is shared with the relevant users or groups. Table selection and instructions define what the space can answer, but sharing controls who can access it. Once shared, users with appropriate Unity Catalog privileges on the underlying table can ask natural-language questions and receive generated SQL results.

Answer

Create a Databricks SQL dashboard that mirrors the same table and link it to the Genie space.

Answer

Enable serverless SQL warehouse compute for the workspace so Genie can run queries.

Answer

Convert the table into a Delta Live Tables pipeline so Genie can read it.

Question 5

A data analyst is configuring an AI/BI Genie Space for a product team. The team wants to ask questions like 'How many active users do we have?' and 'What is the average session duration?' The analyst has provided instructions defining 'active user' as a user who has logged in within the last 30 days and 'session duration' as the time between login and logout. However, Genie still returns incorrect counts because it includes users who have logged in but not logged out. Which additional configuration should the analyst apply to fix this?

Accepted Answer

Update the instructions to specify that session duration should only be calculated for sessions with a logout event. The analyst should update the instructions to specify that session duration is only calculated for sessions with a logout event. This ensures Genie correctly filters out incomplete sessions, fixing the average session duration calculation. Instructions are the primary way to convey such business rules to Genie.

Answer

Add a sample query that calculates active users based on the last 30 days

Answer

Add a column description for the logout timestamp indicating it can be null

Answer

Create a view that filters out sessions without a logout event

Question 6

An analyst is setting up an AI/BI Genie Space for a sales dataset. The analyst wants to ensure that Genie can answer questions about "quarterly revenue" correctly. The dataset has a `revenue` column and an `order_date` column. Which TWO actions should the analyst take? (Choose two.)

Accepted Answer

Add an instruction defining "quarterly revenue" as the sum of revenue grouped by quarter derived from order_date.. To ensure Genie correctly computes quarterly revenue, the analyst should define the calculation in an instruction and improve column metadata by renaming revenue to a clear, descriptive name. The instruction provides the aggregation logic, while the rename strengthens the semantic mapping.

Answer

Add a comment to the revenue column stating it is the revenue amount in USD.

Answer

Add a comment to the order_date column stating it is the date of the order.

Answer

Create a view that pre-aggregates revenue by quarter and add it to the Genie Space.

Question 7

An analytics team is building an AI/BI Genie space to allow business users to query sales data using natural language. After setting up the base tables, the initial user questions return inaccurate filter values because the LLM struggles to map colloquial region names to the exact string codes stored in the database. What is the most effective feature within AI/BI Genie to resolve this mapping issue without modifying the underlying physical tables?

Accepted Answer

Configure table and column descriptions, add explicit instructions, and provide verified queries demonstrating the correct region mappings.. Adding instructions, descriptions, and verified queries to the Genie space gives the underlying model precise semantic context about colloquial terms, business definitions, and expected filters. This targeted guidance steers natural language translation toward the correct database columns and values without requiring costly data transformations or restructuring of source tables in the data lakehouse.

Answer

Create a materialized view containing hardcoded string mappings for every possible regional variation queried by business users.

Answer

Enable automatic schema inference and let the Genie space rebuild its internal vector embeddings from scratch overnight.

Answer

Modify the source table column constraints to reject any query that does not use the exact database region code.

Question 8

Which component of an AI/BI Genie space is responsible for defining the scope of data available to a user and ensuring that the natural language model only references authorized tables?

Accepted Answer

The Genie space instructions and metadata definition. Genie spaces rely on the definition of data instructions and schema mappings within the space configuration. By explicitly linking specific tables and columns, the system enforces access control and ensures the LLM does not hallucinate using external data. This metadata-driven approach is critical for maintaining data governance and security while enabling self-service analytics for business users within the Databricks ecosystem.

Answer

The Unity Catalog Data Explorer integration

Answer

The Databricks SQL Warehouse access policy

Answer

The workspace-level workspace AI configuration

Question 9

What is the primary purpose of adding 'Instructions' to a Genie space in Databricks?

Accepted Answer

To provide context and guidance for query generation. Instructions serve as a system prompt that guides the AI's behavior, defining business logic, specific terminology, and preferred analytical approaches. By setting these instructions, developers improve the accuracy of query generation, ensuring the AI understands company-specific jargon and data relationships that aren't inherently obvious from table schemas alone. This significantly enhances the user experience and reliability of the natural language interface.

Answer

To automate the deployment of SQL Warehouses

Answer

To enable automatic updates for underlying tables

Answer

To store user credentials for data access

Question 10

A data analyst is setting up a new Genie space. Which TWO of the following are prerequisites for the successful creation and usage of a Genie space?

Accepted Answer

A Unity Catalog-enabled workspace. Genie spaces require a foundational environment where data is discoverable and executable. Unity Catalog provides the necessary governance and metadata, while a SQL Warehouse provides the compute resources to execute the generated code. Without these, the Genie space lacks both the data access layer and the processing capability required to answer user questions, making these two components absolute necessities for the feature to function correctly.

Answer

A pre-trained custom Large Language Model

Answer

A local Python environment with Genie SDK

Answer

A Delta Live Table pipeline with high availability

Question 11

An analyst notices that the Genie space is consistently ignoring a specific column during query generation. What is the most effective way to force the model to consider this column?

Accepted Answer

Add a column comment in Unity Catalog and mention it in instructions. LLMs can sometimes overlook columns if they aren't described clearly in the metadata or instructions. Providing explicit, high-quality descriptions in the table metadata (within Unity Catalog) or adding a specific note in the Genie space instructions ensures the model recognizes the column's semantic value and usage context, forcing it to include the information in its reasoning process during user interactions.

Answer

Rename the column to start with 'Required_'

Answer

Hard-code the column in the SQL Warehouse settings

Answer

Delete and recreate the Genie space

Question 12

Which THREE features are provided by AI/BI Genie spaces to help business users analyze data independently?

Accepted Answer

Conversational natural language querying. Genie spaces empower business users by abstracting complex SQL development. They provide a natural language interface for asking questions, automatic visualization of results for immediate insight, and a feedback loop where users can rate answers to refine the model's future performance. These features collectively reduce the burden on data teams while fostering a self-service culture where users can safely interact with governed data assets.

Answer

One-click deployment of production ETL pipelines

Answer

Automatic generation of unit tests for Python code

Question 13

Which of the following is the best strategy for refining Genie space performance when the model consistently struggles with complex joins?

Accepted Answer

Add primary/foreign key definitions and clarify join logic in instructions. When a Genie space fails on multi-table joins, the underlying issue is often a lack of clear relationship definitions. By updating the table metadata in Unity Catalog (such as primary and foreign key constraints) and using the Genie instructions to explicitly define how tables should be joined, the developer provides the model with the necessary 'map' to build complex queries accurately.

Answer

Flatten all tables into a single wide table

Answer

Increase the number of allowed tables

Answer

Switch to a larger, more expensive SQL Warehouse

Question 14

Who is the primary intended audience for an AI/BI Genie space in a Databricks environment?

Accepted Answer

Business analysts and non-technical stakeholders. Genie spaces are specifically designed to bridge the gap between technical data infrastructure and business users. By providing a natural language interface, they allow non-technical stakeholders to ask questions and explore data without needing to write SQL or understand complex data schemas. This democratizes access to data and reduces dependency on data teams for basic reporting.

Answer

Data engineers building ETL pipelines

Answer

Machine Learning engineers for model training

Answer

System administrators for managing clusters

Question 15

What is the primary implication of granting a user 'Can Use' permission on a Genie space?

Accepted Answer

The user can ask natural language questions. The 'Can Use' permission allows a user to interact with the Genie space via natural language. This provides them the ability to ask questions and view results without giving them the rights to modify the space's instructions or configuration. This permission model follows the principle of least privilege, ensuring that users can perform their analysis without the risk of accidentally altering the underlying configuration.

Answer

The user can modify the Genie space instructions

Answer

The user gains direct access to the SQL Warehouse

Answer

The user becomes the owner of the space

Question 16

Which TWO of the following are best practices for writing instructions in an AI/BI Genie space?

Accepted Answer

Provide clear, concise business logic definitions. Effective Genie instructions are concise, specific, and structured. They should prioritize clarity to prevent ambiguity and ensure the model consistently follows business rules. By focusing on explicit examples and avoiding irrelevant information, developers help the LLM maintain high accuracy and reduce the risk of hallucination, which is vital for building trust with business users who rely on the provided insights.

Answer

Include historical SQL queries for every possible outcome

Answer

Include sensitive security credentials for authentication

Answer

Use long-form essay style descriptions for all tables

Question 17

An analyst wants to ensure that a Genie space only uses the most recent data for all queries. How can this be achieved?

Accepted Answer

Use instructions to mandate filters on date columns. To enforce data freshness, the analyst should instruct the Genie space to use views or filter conditions that point to the latest partitions or versioned tables. By incorporating this logic into the instructions, the developer ensures that the model always applies the necessary filter clauses (like 'WHERE date = CURRENT_DATE') to every generated query, maintaining data integrity without requiring manual input from the users.

Answer

Set the SQL Warehouse to auto-terminate every hour

Answer

Delete old data from the Unity Catalog tables

Answer

Rename tables whenever new data arrives

Question 18

What happens if a user submits a question that requires data from a table NOT explicitly defined in the Genie space configuration?

Accepted Answer

The model will deny the request due to lack of access. Genie spaces are designed with a security-first approach. If a table is not listed in the space's configuration, the model is physically prevented from accessing it. This ensures that users cannot 'force' the AI to query unauthorized or sensitive data outside the intended analytical scope, protecting the organization from data leakage or unauthorized access to proprietary information stored in other parts of the Unity Catalog.

Answer

The model will try to guess the schema of the table

Answer

The model will use the table anyway if the user has access

Answer

The query will execute but return null results

Question 19

Why should an analyst use the 'feedback' feature provided in an AI/BI Genie space interface?

Accepted Answer

To improve the accuracy of future answers. The feedback mechanism is crucial for the iterative improvement of the Genie space. When users rate answers as 'helpful' or 'not helpful,' they provide signal that Databricks uses to refine the model's performance over time. This continuous learning process ensures that the assistant becomes more accurate, more relevant, and better aligned with the specific business context, ultimately providing higher value to the entire user organization.

Answer

To log a support ticket with Databricks Engineering

Answer

To increase the SQL Warehouse query limit

Answer

To export the answer as a CSV file

Question 20

A Data Analyst is configuring an AI/BI Genie Space to allow business users to query sales data. The analyst needs to ensure the model understands specific business logic, such as how to calculate 'Net Revenue' from raw columns. Where should the analyst define this logic to ensure Genie consistently applies these business rules across all user queries?

Accepted Answer

Define the logic in the SQL view metadata or table comments within Unity Catalog.. Defining business logic in the underlying Databricks SQL Warehouse or Unity Catalog perspective is the most reliable way to guide Genie. By providing clear descriptions and semantic definitions within the catalog or view metadata, the LLM-driven engine can correctly interpret business terminology. This ensures that non-technical users receive consistent, accurate results without needing to write complex SQL, directly impacting the trust and adoption of the AI/BI solution within the organization.

Answer

Add the logic as a comment in the user's prompt history.

Answer

Hardcode the business logic into the Genie Space configuration UI.

Answer

Require users to provide the formula in every natural language query.

Databricks-DA-Assoc Developing AI/BI Genie Spaces — All Questions With Answers

A data analyst is setting up an AI/BI Genie Space for the marketing team. They want to provide example questions that users can ask to get started. Which TWO of the following are valid ways to add example questions to a Genie Space? (Choose two.)

A data analyst is configuring an AI/BI Genie Space that includes a table with a column named `rev`. The analyst wants Genie to understand that `rev` means total revenue in USD. The analyst also wants to ensure that when users ask for revenue, Genie uses this column. Which action is most effective?

An analyst is setting up an AI/BI Genie Space for a sales dataset. The analyst wants to ensure that Genie can answer questions about "quarterly revenue" correctly. The dataset has a `revenue` column and an `order_date` column. Which TWO actions should the analyst take? (Choose two.)

Which component of an AI/BI Genie space is responsible for defining the scope of data available to a user and ensuring that the natural language model only references authorized tables?

What is the primary purpose of adding 'Instructions' to a Genie space in Databricks?

A data analyst is setting up a new Genie space. Which TWO of the following are prerequisites for the successful creation and usage of a Genie space?

An analyst notices that the Genie space is consistently ignoring a specific column during query generation. What is the most effective way to force the model to consider this column?

Which THREE features are provided by AI/BI Genie spaces to help business users analyze data independently?

Which of the following is the best strategy for refining Genie space performance when the model consistently struggles with complex joins?

Who is the primary intended audience for an AI/BI Genie space in a Databricks environment?

What is the primary implication of granting a user 'Can Use' permission on a Genie space?

Which TWO of the following are best practices for writing instructions in an AI/BI Genie space?

An analyst wants to ensure that a Genie space only uses the most recent data for all queries. How can this be achieved?

What happens if a user submits a question that requires data from a table NOT explicitly defined in the Genie space configuration?

Why should an analyst use the 'feedback' feature provided in an AI/BI Genie space interface?

Which primary resource must be granted to users for them to successfully interact with an AI/BI Genie Space to generate insights?

Refer to the exhibit. A developer is configuring a Genie Space. The model is still including discounts in its revenue calculations despite the instruction. What is the most likely cause?

Exhibit

Which TWO actions should an analyst take to improve the accuracy of an AI/BI Genie Space when users report that it frequently hallucinates metric definitions?

An analyst notices that the AI/BI Genie Space is generating queries that take too long to execute. The underlying data is stored in partitioned tables. What is the most effective way to help the Genie generate more performant SQL?

You are auditing access to several AI/BI Genie Spaces. You discover that a group of users can ask questions but cannot see the underlying source tables in the Catalog Explorer. Is this a functional issue?

Which THREE of the following are essential components of a well-architected AI/BI Genie Space setup?

An analyst is setting up a Genie Space to handle financial reporting. They want the model to always group results by 'fiscal_quarter'. How should they enforce this requirement?

A business user asks a Genie Space, 'Show me the revenue by product.' The model returns an error. What is the most common reason for this failure in a properly configured environment?

Refer to the exhibit. The Genie Space output is consistently truncated. What is the most likely cause?

Exhibit

When designing an AI/BI Genie Space, how can an analyst prevent the model from accessing PII (Personally Identifiable Information) columns in a sensitive table?

A data analyst is configuring an AI/BI Genie Space to allow business users to query sales data. The analyst needs to ensure the Space uses the most performant and governed data source available in the Unity Catalog. Which configuration should the analyst prioritize?

A Genie Space is producing inaccurate results when asked about 'Customer Lifetime Value'. The analyst realizes the AI model is misinterpreting the calculation logic. What is the most effective way to improve the AI's accuracy for this specific business term?

An analyst is preparing a Genie Space and wants to ensure users get the most accurate answers while maintaining security. Which TWO actions should the analyst take? (Choose two)

Refer to the exhibit. An analyst is reviewing the configuration JSON for a Genie Space. Why is the 'instructions' field critical in this scenario?

Exhibit

A data analyst is creating a new AI/BI Genie Space for the sales team. They want to add a trusted table that contains curated sales data. Which of the following is the correct way to add a table to the Genie Space?

An analyst is configuring an AI/BI Genie Space and wants to ensure that the model correctly interprets the term 'revenue' as the sum of the 'sales_amount' column. Which action should the analyst take?

An analyst is configuring an AI/BI Genie Space for a retail dataset. The analyst wants Genie to map the business term "top sellers" to a specific calculation that ranks products by total units sold. Where should the analyst define this mapping?

A business analyst is using an AI/BI Genie Space to explore customer data. They ask, 'What is the average customer age?' The Genie Space returns a result. Which underlying Databricks component does Genie use to execute the generated SQL query?

An analyst is configuring an AI/BI Genie Space and wants to ensure that the model only uses a specific SQL warehouse for query execution. Where should the analyst configure this setting?

A data analyst is configuring an AI/BI Genie Space for a customer support dataset. The analyst notices that when users ask "how many open tickets per agent," Genie sometimes counts all tickets instead of only open ones. The analyst wants to fix this. What should the analyst do?

Databricks-DA-Assoc Developing AI/BI Genie Spaces — All Questions With Answers

A data analyst is setting up an AI/BI Genie Space for the marketing team. They want to provide example questions that users can ask to get started. Which TWO of the following are valid ways to add example questions to a Genie Space? (Choose two.)

A data analyst is configuring an AI/BI Genie Space that includes a table with a column named `rev`. The analyst wants Genie to understand that `rev` means total revenue in USD. The analyst also wants to ensure that when users ask for revenue, Genie uses this column. Which action is most effective?

An analyst is setting up an AI/BI Genie Space for a sales dataset. The analyst wants to ensure that Genie can answer questions about "quarterly revenue" correctly. The dataset has a `revenue` column and an `order_date` column. Which TWO actions should the analyst take? (Choose two.)

Which component of an AI/BI Genie space is responsible for defining the scope of data available to a user and ensuring that the natural language model only references authorized tables?

What is the primary purpose of adding 'Instructions' to a Genie space in Databricks?

A data analyst is setting up a new Genie space. Which TWO of the following are prerequisites for the successful creation and usage of a Genie space?

An analyst notices that the Genie space is consistently ignoring a specific column during query generation. What is the most effective way to force the model to consider this column?

Which THREE features are provided by AI/BI Genie spaces to help business users analyze data independently?

Which of the following is the best strategy for refining Genie space performance when the model consistently struggles with complex joins?

Who is the primary intended audience for an AI/BI Genie space in a Databricks environment?

What is the primary implication of granting a user 'Can Use' permission on a Genie space?

Which TWO of the following are best practices for writing instructions in an AI/BI Genie space?

An analyst wants to ensure that a Genie space only uses the most recent data for all queries. How can this be achieved?

What happens if a user submits a question that requires data from a table NOT explicitly defined in the Genie space configuration?

Why should an analyst use the 'feedback' feature provided in an AI/BI Genie space interface?

Which primary resource must be granted to users for them to successfully interact with an AI/BI Genie Space to generate insights?

Refer to the exhibit. A developer is configuring a Genie Space. The model is still including discounts in its revenue calculations despite the instruction. What is the most likely cause?

Exhibit

Which TWO actions should an analyst take to improve the accuracy of an AI/BI Genie Space when users report that it frequently hallucinates metric definitions?

An analyst notices that the AI/BI Genie Space is generating queries that take too long to execute. The underlying data is stored in partitioned tables. What is the most effective way to help the Genie generate more performant SQL?

You are auditing access to several AI/BI Genie Spaces. You discover that a group of users can ask questions but cannot see the underlying source tables in the Catalog Explorer. Is this a functional issue?

Which THREE of the following are essential components of a well-architected AI/BI Genie Space setup?

An analyst is setting up a Genie Space to handle financial reporting. They want the model to always group results by 'fiscal_quarter'. How should they enforce this requirement?

A business user asks a Genie Space, 'Show me the revenue by product.' The model returns an error. What is the most common reason for this failure in a properly configured environment?

Refer to the exhibit. The Genie Space output is consistently truncated. What is the most likely cause?

Exhibit

When designing an AI/BI Genie Space, how can an analyst prevent the model from accessing PII (Personally Identifiable Information) columns in a sensitive table?

A data analyst is configuring an AI/BI Genie Space to allow business users to query sales data. The analyst needs to ensure the Space uses the most performant and governed data source available in the Unity Catalog. Which configuration should the analyst prioritize?

A Genie Space is producing inaccurate results when asked about 'Customer Lifetime Value'. The analyst realizes the AI model is misinterpreting the calculation logic. What is the most effective way to improve the AI's accuracy for this specific business term?

An analyst is preparing a Genie Space and wants to ensure users get the most accurate answers while maintaining security. Which TWO actions should the analyst take? (Choose two)

Refer to the exhibit. An analyst is reviewing the configuration JSON for a Genie Space. Why is the 'instructions' field critical in this scenario?

Exhibit

A data analyst is creating a new AI/BI Genie Space for the sales team. They want to add a trusted table that contains curated sales data. Which of the following is the correct way to add a table to the Genie Space?

An analyst is configuring an AI/BI Genie Space and wants to ensure that the model correctly interprets the term 'revenue' as the sum of the 'sales_amount' column. Which action should the analyst take?

An analyst is configuring an AI/BI Genie Space for a retail dataset. The analyst wants Genie to map the business term "top sellers" to a specific calculation that ranks products by total units sold. Where should the analyst define this mapping?

A business analyst is using an AI/BI Genie Space to explore customer data. They ask, 'What is the average customer age?' The Genie Space returns a result. Which underlying Databricks component does Genie use to execute the generated SQL query?

An analyst is configuring an AI/BI Genie Space and wants to ensure that the model only uses a specific SQL warehouse for query execution. Where should the analyst configure this setting?

A data analyst is configuring an AI/BI Genie Space for a customer support dataset. The analyst notices that when users ask "how many open tickets per agent," Genie sometimes counts all tickets instead of only open ones. The analyst wants to fix this. What should the analyst do?