Courseiva

PDE Preparing and Using Data for Analysis Practice Question

A machine learning engineer needs to deploy a custom TensorFlow model for online predictions with low latency. The model is already trained and saved in SavedModel format. Which Vertex AI service 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 Prediction

Vertex AI Prediction allows you to deploy custom models (including TensorFlow SavedModel) to an endpoint for online predictions. It supports autoscaling and low-latency serving.

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 Workbench

    Why it's wrong here

    Workbench provides managed notebook environments for developing and training models, not serving them. It tempts because the model was built in a notebook, but online low-latency prediction needs a deployed Endpoint, which Workbench does not supply.

  • ✓

    Vertex AI Prediction

    Why this is correct

    Vertex AI Prediction deploys the SavedModel to an endpoint serving online predictions with low latency, satisfying the stem's requirement. Unlike batch prediction, it provisions a persistent endpoint for real-time inference, and unlike custom training, it consumes the already-trained artefact directly without retraining.

  • ✗

    Vertex AI Feature Store

    Why it's wrong here

    Feature Store centralises feature storage and serving for training and prediction, but it does not host models. It tempts because online prediction consumes features, yet the SavedModel itself must be deployed to a Vertex AI Endpoint, which Feature Store cannot provide.

  • ✗

    Vertex AI AutoML

    Why it's wrong here

    AutoML trains and tunes models from your data, so it cannot serve an already-trained SavedModel. It tempts because it also offers prediction endpoints, but those host AutoML-generated models; deploying custom TensorFlow artefacts requires Vertex AI Endpoints instead.

About these practice questions

This PDE question is part of Courseiva's 747-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 →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This PDE 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 PDE exam.