hardMultiple Select
Generative AI Leader Practice Question: Deploying a generative AI chatbot for customer…
A company is deploying a generative AI chatbot for customer support. They want to ensure that the chatbot does not generate harmful content and that they can customize the safety thresholds. Which TWO features in Vertex AI should they use? (Select 2)
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
✓
Custom safety settings (adjustable thresholds)
Option B (Custom safety settings with adjustable thresholds) is correct because Vertex AI's generative AI safety controls let you configure per-category harm thresholds (for example, blocking more or less aggressively for hate speech, harassment, sexually explicit, and dangerous content), which directly satisfies the requirement to customize safety thresholds. Option D (Safety filters) is correct because these filters are the mechanism that actually evaluates model prompts and responses against harm categories and blocks or allows content, preventing the chatbot from generating harmful output. Together, safety filters provide the enforcement while custom safety settings provide the tunable thresholds the company wants. Option A (AutoML Tables) is incorrect because it is a tabular ML training/prediction service, not a content-safety feature. Option C (Model Cards) is incorrect because it documents model details, intended use, and evaluations but does not filter or block harmful content. Option E (People + AI Guidebook) is incorrect because it is a design guidance resource, not a runtime safety control in Vertex AI.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
AutoML Tables
Why it's wrong here
AutoML Tables builds tabular classification and regression models from structured datasets; it offers no content filtering or configurable safety thresholds for generative text. It would be the right choice for predicting churn or sales from spreadsheet-style data, not for constraining chatbot output.
- ✓
Custom safety settings (adjustable thresholds)
Why this is correct
Custom safety settings let you tune threshold levels per harm category — hate speech, harassment, sexually explicit, dangerous content — directly satisfying the requirement for adjustable safety thresholds. Configuring these on the Vertex AI model blocks responses exceeding your chosen sensitivity, preventing harmful chatbot output while retaining granular control over filtering strictness.
- ✗
Model Cards
Why it's wrong here
Model Cards document a model's intended use, limitations and evaluation metrics for governance and transparency; they do not intercept or block harmful generations, nor expose adjustable safety thresholds. They would be correct when publishing model provenance and fairness information to stakeholders.
- ✓
Safety filters
Why this is correct
Safety filters automatically detect and block harmful categories such as harassment, hate speech and dangerous content in both prompts and responses. This satisfies the stem's requirement that the chatbot avoid generating harmful content during customer support interactions.
- ✗
People + AI Guidebook
Why it's wrong here
The People + AI Guidebook is human-centred design guidance for building AI products, not a runtime control. It cannot filter harmful chatbot responses or let you tune safety thresholds. It would be the right choice when shaping UX, onboarding and user trust during product design.
Go deeper
Related to this question
About these practice questions
Courseiva writes every Generative AI Leader question from scratch — 1,008 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.