Databricks-DA-Assoc Developing AI/BI Genie Spaces Practice Question
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?
⚠ Common exam trap
Candidates frequently think that rebuilding the underlying physical tables or adding new indexes is required, ignoring the power of system instructions for guiding LLM query generation.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Modify the system instructions to require filtering on partition keys.
Genie models are highly responsive to context. By adding explicit instructions about filtering on partition columns, such as 'always filter by date or region,' the model learns to include these constraints in its generated SQL. This ensures that the generated queries prune data partitions effectively, significantly reducing query runtime and resource consumption on the SQL Warehouse, which directly improves the end-user experience for all business users.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Instruct the model to use 'SELECT *' to get all data at once.
Why it's wrong here
Using 'SELECT *' is a performance anti-pattern. It forces the system to read and return unnecessary data, leading to higher I/O and latency. For performant SQL, the model should be instructed to select only the required columns and apply filters that leverage existing table partitioning or indexing strategies.
- ✓
Modify the system instructions to require filtering on partition keys.
Why this is correct
Explicitly instructing the model to filter by partition keys (like date or region) ensures that every query generated by the AI is optimized for performance. By guiding the model to narrow the scope of the data scan, you prevent full table scans and reduce the load on the warehouse.
- ✗
Increase the SQL Warehouse cluster size to handle larger queries.
Why it's wrong here
Increasing cluster size addresses the symptoms of poor performance rather than the root cause. It is a costly solution that does not solve the issue of inefficient query generation. Optimization should start by ensuring that the generated SQL is efficient, as even a large cluster will struggle with unoptimized queries.
- ✗
Use a different LLM model within the Genie settings.
Why it's wrong here
Changing the LLM model does not inherently address the efficiency of the generated SQL. The underlying issue is likely the lack of guidance on data structure and partitioning. Optimization requires providing the model with the correct context, not merely swapping the underlying engine for another standard model.
About these practice questions
One of 291 original Databricks-DA-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-DA-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-DA-Assoc exam.