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.
Go deeper
Related to this question
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 →
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.