Databricks-DA-Assoc Developing AI/BI Genie Spaces Practice Question
A data analyst is tuning an AI/BI Genie space used by the finance department. Users report that Genie sometimes returns plausible but incorrect aggregations, and that questions referencing 'net revenue' produce inconsistent results. The analyst wants to improve grounding and reliability. Which TWO actions should the analyst take? (Choose two.)
⚠ Common exam trap
The trap here is treating inconsistent business-term interpretation as a compute or permissions issue, when the real fix is supplying explicit definitions and worked examples.
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
✓
Add a general instruction in the Genie space that defines net revenue as gross revenue minus returns and discounts.
Inconsistent results for a business term like net revenue are best resolved by encoding the definition explicitly and demonstrating it. General instructions provide the textual rule, while example SQL queries show the exact joins and arithmetic. Together they ground the model's interpretation and reduce plausible-but-incorrect outputs. Compute scaling and access restrictions do not address semantic ambiguity.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Remove all tables except one from the Genie space so the model has fewer choices.
Why it's wrong here
Reducing tables can lower ambiguity in some cases, but removing all but one finance table would strip away data needed for returns and discounts, making correct net revenue calculations impossible. The reported issue is definitional inconsistency, not excessive table count. A blunt reduction sacrifices capability without guaranteeing accuracy, so it is not an appropriate tuning action here.
- ✓
Add a general instruction in the Genie space that defines net revenue as gross revenue minus returns and discounts.
Why this is correct
General instructions are the mechanism for encoding business definitions that apply across many questions. Defining net revenue explicitly removes ambiguity and steers the model toward a consistent formula. This directly addresses the inconsistent results users reported, because the model no longer has to guess which columns or operations constitute net revenue. It is a targeted, supported way to improve grounding.
- ✓
Add example SQL queries to the Genie space that demonstrate correct net revenue calculations against the finance tables.
Why this is correct
Example SQL queries act as few-shot demonstrations that show Genie the exact join and aggregation patterns expected. When users ask about net revenue, the model can pattern-match against these examples, reducing plausible-but-wrong outputs. Combining examples with textual definitions reinforces both the formula and the correct table usage, which is why this action complements the instruction-based fix.
- ✗
Switch the Genie space to use a larger SQL warehouse so the model has more compute for reasoning.
Why it's wrong here
SQL warehouse size affects query execution speed, not the semantic reasoning that maps 'net revenue' to a formula. Genie's interpretation is driven by metadata, instructions, and examples rather than warehouse capacity. Upsizing compute would increase cost without fixing the inconsistent aggregations. It misidentifies a semantic grounding problem as a performance problem.
- ✗
Restrict the space to read-only access for all users so no one can modify the underlying data.
Why it's wrong here
Read-only access prevents data modification but does not influence how Genie interprets business terms. The inconsistency stems from undefined semantics, not from users altering tables. Applying read-only restrictions would not change generated SQL or aggregation logic and could even hinder legitimate workflows. It is a security measure, not a grounding improvement.
Visual reference
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.