Courseiva
Monitoring ML SolutionsmediumMultiple ChoiceObjective-mapped

PMLE Monitoring ML Solutions Practice Question

An ML engineer wants to monitor the latency of online predictions from a Vertex AI Endpoint. They need to track p50, p95, and p99 latency over time and set up alerts if p99 exceeds 1 second. Which approach should they take?

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

Configure a Cloud Monitoring dashboard using the built-in Vertex AI Endpoint metrics for latency

Cloud Monitoring can ingest metrics from Vertex AI Endpoints, including prediction latency distributions (p50, p95, p99). Alerts can be configured on these metrics.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Configure a Cloud Monitoring dashboard using the built-in Vertex AI Endpoint metrics for latency

    Why this is correct

    Built-in metrics include latency percentiles; alerts can be set directly.

  • Use Cloud Monitoring custom metrics and publish latency percentiles from the application code

    Why it's wrong here

    Unnecessary; Vertex AI Endpoints automatically expose latency metrics.

  • Enable request/response logging to BigQuery and calculate latency percentiles using SQL queries

    Why it's wrong here

    This approach is possible but adds latency and is not real-time; Cloud Monitoring is native.

  • Use Vertex AI Model Monitoring to track prediction latency

    Why it's wrong here

    Model Monitoring tracks feature skew/drift, not latency.

About these practice questions

One of 990 original PMLE 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 →

How Courseiva writes practice questions · Editorial policy

Same concept, more angles

2 more ways this is tested on PMLE

These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.

Variation 1. An ML engineer wants to monitor the performance of a Vertex AI Endpoint. Which TWO metrics are available in Cloud Monitoring for Vertex AI Endpoints? (Choose 2)

easy
  • A.Model accuracy
  • B.Error count
  • C.Feature skew score
  • D.SHAP values
  • E.Prediction latency (p50, p95, p99)

Why B: Cloud Monitoring for Vertex AI Endpoints includes metrics like prediction latency (p50, p95, p99) and error count/rate. CPU/GPU utilization is also available for endpoint machines.

Variation 2. An ML engineer needs to monitor the online prediction latency of a Vertex AI Endpoint. Which metrics should they look at in Cloud Monitoring?

easy
  • A.p50, p95, p99 latency
  • B.Request count and error rate
  • C.Skew and drift scores
  • D.CPU/GPU utilization

Why A: Cloud Monitoring provides latency metrics for Vertex AI Endpoints, including p50, p95, and p99 latency, which are key for understanding performance.

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This PMLE 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 PMLE exam.