hardMultiple Choice
Generative AI Leader Practice Question: Wants to ensure that when their employees use the…
An organization wants to ensure that when their employees use the Gemini API via Vertex AI, the grounding searches are restricted to internal company knowledge bases rather than the public web. Which feature should they enable?
⚠ Common exam trap
Many exam-takers confuse 'Google Search Grounding' (which uses the public web) with Vertex AI Search's private data grounding, leading them to select Option C instead of recognizing that Vertex AI Search with private data indexing is the correct solution for internal grounding.
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
✓
Vertex AI Search (with private data indexing)
Vertex AI Search allows organizations to index private, internal data sources (e.g., documents, databases) and use them as the grounding source for Gemini API queries. By enabling this feature, grounding searches are restricted to the indexed private knowledge base, ensuring no public web results are used. This directly meets the requirement to keep grounding internal.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enterprise Data Governance on Vertex AI
Why it's wrong here
Enterprise Data Governance covers classification, lineage and policy controls over data assets; it does not configure the retrieval source used by grounding. It is tempting because governance sounds like it governs what the model may access, and it would be correct when the goal is cataloguing or policy enforcement across Vertex AI datasets.
- ✗
VPC Service Controls
Why it's wrong here
VPC Service Controls builds a perimeter around Google Cloud resources to block data exfiltration, but it does not choose which corpus a grounding request queries. It is tempting because it governs data boundaries, and it would be correct when the requirement is preventing data leaving a project rather than selecting internal knowledge bases.
- ✗
Google Search Grounding
Why it's wrong here
Google Search Grounding deliberately retrieves from the public web, which is the opposite of the stated requirement. It is tempting because it is the default grounding option and improves factual accuracy, and it would be correct when answers must reflect current public information rather than internal documents.
- ✓
Vertex AI Search (with private data indexing)
Why this is correct
Vertex AI Search indexes private data sources, so grounding queries hit internal knowledge bases instead of the public web. This satisfies the restriction constraint directly, since the API's default grounding would otherwise reach public sources.
Go deeper
Related to this question
About these practice questions
One of 1,008 original Generative AI Leader 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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.