mediumMultiple Choice
Generative AI Leader Practice Question: A company uses Vertex AI Agent Builder to create…
A company uses Vertex AI Agent Builder to create a customer support agent. They need the agent to answer questions about order status by calling an internal API. Which Vertex AI feature should they use?
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 Extensions
Extensions in Vertex AI Agent Builder allow the agent to call external APIs (including internal ones) as tools during conversation.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Vertex AI RAG Engine
Why it's wrong here
RAG Engine retrieves from indexed documents or corpora; it cannot execute a live API call to fetch current order status. It tempts because RAG grounds responses in enterprise knowledge sources, which is correct when answers live in static documentation rather than transactional systems.
- ✓
Vertex AI Extensions
Why this is correct
Vertex AI Extensions connect the agent to external systems and APIs, letting it execute the internal order-status API call at runtime. This satisfies the requirement for live order data rather than relying on static model knowledge or grounding documents alone.
- ✗
Grounding with Google Search
Why it's wrong here
Grounding with Google Search queries public web content, not the company's internal order API. It tempts because grounding reduces hallucination for general-knowledge questions, which is correct when answers depend on current public information rather than private systems.
- ✗
Vertex AI Model Garden
Why it's wrong here
Model Garden is a catalogue for discovering, testing and deploying foundation models; it provides no tool-calling mechanism to reach the internal API. It tempts because it is the right place to select a model, which is correct when the task is model choice rather than live data retrieval.
Go deeper
Related to this question
About these practice questions
This Generative AI Leader question is part of Courseiva's 1,008-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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.