Generative AI Leader Google Cloud's Generative AI Offerings Practice Test 2 — 15 Questions

Question 1

A company is building a customer support chatbot using Vertex AI Agent Builder. They want the agent to answer questions based on internal knowledge base documents stored in Cloud Storage. Which feature should they configure to ensure the agent can retrieve relevant information from these documents?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Enable grounding with a data store. Vertex AI Agent Builder uses grounding to connect the agent to external data sources, such as documents stored in Cloud Storage. By enabling grounding with a data store, the agent can retrieve and reference relevant information from the knowledge base documents in real time, ensuring accurate and context-aware responses without requiring model retraining.

Answer

Deploy the agent to a Vertex AI endpoint

Answer

Fine-tune a Gemini model on the knowledge base

Answer

Configure a safety filter to block irrelevant queries

Question 2

A data scientist is using Vertex AI Model Registry to manage multiple versions of a custom text classification model. They need to ensure that only the version that passes all evaluation metrics can be deployed to a Vertex AI Endpoint for online predictions. What deployment strategy should they use?

Accepted Answer

Set up continuous evaluation with model monitoring to auto-promote versions that meet thresholds. Vertex AI Model Registry supports continuous evaluation pipelines that automatically promote a model version to a 'default' or 'deployed' status only when it meets predefined evaluation thresholds (e.g., accuracy, F1 score). This ensures that only the version passing all metrics is eligible for deployment to a Vertex AI Endpoint, enabling automated, gated rollouts without manual intervention.

Answer

Use A/B testing between versions and manually select the best performer

Answer

Manually track version IDs and deploy the latest version

Answer

Deploy all versions to a single endpoint and route traffic manually

Question 3

An organization is using Vertex AI Gemini API for a multimodal chatbot. They notice that the model sometimes provides incorrect information with high confidence. They want to reduce hallucinations without retraining the model. What is the most effective approach?

Accepted Answer

Provide ground-truth context from a knowledge base using grounding. Grounding with a knowledge base is the most effective approach because it forces the model to base its responses on verified, external data rather than relying solely on its parametric knowledge. By providing ground-truth context via Vertex AI's grounding feature, the model can cross-reference its outputs with authoritative sources, significantly reducing the likelihood of hallucinations. This method directly addresses the root cause of incorrect high-confidence responses without requiring retraining.

Answer

Increase the temperature parameter to make the model more creative

Answer

Reduce the maximum output tokens to force concise answers

Answer

Adjust safety settings to filter uncertain responses

Question 4

A retailer wants to use generative AI to write product descriptions automatically. They have a large dataset of existing product descriptions and need to customize a foundation model for their brand voice. Which Vertex AI feature should they use?

Accepted Answer

Vertex AI custom model tuning. Vertex AI custom model tuning (Option D) is correct because it allows the retailer to fine-tune a foundation model on their proprietary dataset of existing product descriptions, adapting the model's output to match their specific brand voice and style. This process adjusts the model's weights using supervised learning on the retailer's data, enabling personalized and consistent content generation that generic prompt engineering cannot achieve.

Answer

Vertex AI Search with grounding

Answer

Prompt design with the Gemini API directly

Answer

Vertex AI Model Evaluation

Question 5

A financial services firm is using Vertex AI to generate investment reports. They need to ensure that the model outputs are explainable and comply with regulatory requirements. Which Vertex AI feature should they use?

Accepted Answer

Vertex Explainable AI. Vertex Explainable AI provides feature attributions and explanations for model predictions, which is essential for financial services firms that must comply with regulatory requirements like the EU's GDPR or the US SEC's model risk management guidelines. It helps auditors and stakeholders understand why a model generated a specific investment report output, ensuring transparency and accountability in AI-driven decisions.

Answer

Vertex AI Model Registry

Answer

Vertex AI Safety Settings

Answer

Vertex AI AutoML

Question 6

A healthcare company is building a chatbot to answer patient queries using Vertex AI Agent Builder. They want to ensure the chatbot only uses approved medical references and does not generate unverified advice. How should they configure the agent?

Accepted Answer

Set up grounding with a private data store containing verified medical documents. Vertex AI Agent Builder supports grounding with private data stores, which allows the agent to restrict its responses to only the information contained in the verified medical documents. This ensures the chatbot does not generate unverified advice by grounding its outputs in a trusted, curated dataset rather than relying on the model's general training data.

Answer

Enable strict safety filters to block any medical advice

Answer

Increase the temperature parameter to get more diverse responses

Answer

Use Vertex AI Model Monitoring to track answer accuracy

Question 7

Which TWO actions can help reduce latency for an online prediction endpoint served by a large language model on Vertex AI? (Select TWO.)

Accepted Answer

Enable response caching for frequent similar queries. Enabling response caching for frequent similar queries reduces latency by serving cached predictions instead of recomputing them. This is particularly effective for large language models where inference is computationally expensive, as it avoids redundant processing for identical or semantically similar requests. Option D is correct because deploying a smaller distilled version of the model reduces the computational cost per inference, directly lowering latency. Distillation compresses the model while retaining most of its accuracy, making it faster to run predictions.

Answer

Increase the max input token limit to capture more context

Answer

Use automatic scaling to add more replicas

Answer

Set the model to preemptible instances

Question 8

Which THREE capabilities does Vertex AI Agent Builder provide out of the box? (Select THREE.)

Accepted Answer

Automatic escalation to human agents when confidence is low. Vertex AI Agent Builder provides out-of-the-box capabilities including automatic escalation to human agents when confidence is low (A), grounding with enterprise data sources like Cloud Storage and BigQuery (D), and pre-built customer service and sales agents (E). These features enable rapid deployment of conversational AI agents without custom development.

Answer

Fine-tuning of foundation models using custom datasets

Answer

Enterprise search over internal documents

Question 9

Which TWO safety features are available in Vertex AI Gemini API? (Select TWO.)

Accepted Answer

Safety filters for categories like hate speech and harassment. The Vertex AI Gemini API includes built-in safety filters that automatically detect and block harmful content across categories such as hate speech, harassment, sexually explicit material, and dangerous content. These filters operate at the API level, analyzing both input prompts and model responses to enforce Google's AI safety policies before returning results to the user.

Answer

Model-level encryption at rest

Answer

Automatic redaction of personally identifiable information (PII)

Answer

Integration with Cloud Data Loss Prevention (DLP)

Question 10

A data scientist runs the above command to upload a model to Vertex AI Model Registry. The model is a TensorFlow 2.6 model trained on tabular data. After deployment to an endpoint, the prediction latency is higher than expected. What is the most likely cause?

Accepted Answer

The container image used is CPU-only, but a GPU-accelerated image would improve latency. Deploying a TensorFlow 2.6 model trained on tabular data with a CPU-only container image will result in higher latency compared to using a GPU-accelerated image. GPU acceleration significantly speeds up matrix operations and inference for TensorFlow models, especially when handling multiple prediction requests concurrently. The Vertex AI Model Registry allows you to specify a custom container, and choosing a GPU-enabled image (e.g., us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest vs. the GPU variant) directly impacts inference performance.

Answer

The artifact URI points to a single file instead of a directory

Answer

The model should be uploaded with a different display name

Answer

The model is uploaded to the wrong region

Question 11

A developer is configuring a Vertex AI Agent Builder agent to use grounding. They receive the above error when calling the API. What is the most likely cause?

Accepted Answer

The data store has not been created in the specified project. The error message indicates that the data store resource cannot be found in the specified Google Cloud project. Vertex AI Agent Builder requires the data store to exist and be fully provisioned in the same project as the agent before grounding can be configured. If the data store ID or project ID is incorrect, or the data store has not been created, the API will return a 'not found' error.

Answer

The data store was just created and is not yet propagated

Answer

The agent is not authenticated to access the data store

Answer

The grounding configuration is missing required permissions

Question 12

A company is using Vertex AI Generative AI Studio to iterate on a prompt template. They want to save and organize multiple versions of prompts. Which TWO features should they use?

Accepted Answer

Version history. Version history (B) is correct because it allows users to track, compare, and revert to previous iterations of a prompt template directly within Generative AI Studio. This feature is essential for managing the iterative development process, as it automatically saves snapshots of each change, enabling teams to audit and restore earlier versions without manual backup.

Answer

Model Garden

Answer

Parameter sliders

Answer

Run button

Question 13

The exhibit shows the response from a model deployed on Vertex AI that includes safety attributes. The application must reject any prediction where the toxicity score exceeds 0.8. Based on the response, what action should the application take?

Accepted Answer

Reject the prediction because the toxicity score exceeds 0.8.. The response from the model includes a safety attribute with a toxicity score of 0.9, which exceeds the application's threshold of 0.8. Vertex AI safety attributes provide scores for categories like toxicity, insult, and sexual content, and the application must enforce its own rejection logic based on these scores. Since the toxicity score is above the defined threshold, the application should reject the prediction to comply with safety policies.

Answer

Retry the request with a lower temperature.

Answer

Display the prediction because the insult score is below 0.8.

Answer

Log the prediction but still display it.

Question 14

A company is building a document summarization tool using Vertex AI Gemini API. They notice that the model sometimes returns incomplete summaries that miss key points. Which approach is most likely to improve summary quality without increasing token usage significantly?

Accepted Answer

Refine the system instruction to specify the desired summary format and key elements to include. Refining the system instruction directly addresses the root cause of incomplete summaries by providing explicit guidance on the desired output format and key elements to include. This approach improves the model's adherence to the task without increasing the number of input or output tokens, as it only modifies the instruction text, not the document length or generation limits.

Answer

Increase the context window to include more of the document

Answer

Switch to a larger Gemini model (e.g., from 1.0 Pro to 1.5 Pro)

Answer

Increase the max output token limit to allow longer summaries

Question 15

A financial institution wants to deploy a custom fine-tuned model for loan approval recommendations. They must ensure compliance with regulatory requirements, including explainability and bias monitoring. Which combination of Google Cloud services and practices best addresses these needs?

Accepted Answer

Fine-tune a foundation model using a custom training pipeline, then deploy with Vertex AI Model Monitoring and Vertex AI Explainable AI. It combines custom fine-tuning of a foundation model (allowing domain-specific adaptation for loan approval logic) with Vertex AI Model Monitoring (for bias detection and drift monitoring) and Vertex AI Explainable AI (for feature attribution and regulatory explainability). This combination directly addresses the dual regulatory requirements of explainability and bias monitoring while leveraging generative AI capabilities.

Answer

Use Vertex AI Search with grounding on internal policies and enable AutoML for model training

Answer

Deploy a pre-built model from Model Garden and use Vertex AI Model Registry

Answer

Use Vertex AI AutoML for tabular data to train the model and enable Vertex AI Model Monitoring for bias