PMLE Practice Question: Refer to the exhibit

Exhibit

Refer to the exhibit.
```
{
  "insertId": "abc123",
  "jsonPayload": {
    "predictions": [0.98, 0.12],
    "modelVersionId": "1",
    "latencyMs": 450,
    "region": "us-central1"
  },
  "resource": {
    "type": "vertex_ai_endpoint",
    "labels": {
      "endpoint_id": "1234",
      "model_id": "model-xyz"
    }
  },
  "severity": "INFO",
  "timestamp": "2024-03-15T10:30:00Z"
}
```

Refer to the exhibit. A data scientist notices that predictions from a deployed model are taking longer than expected. Which Cloud Monitoring metric should be inspected first to identify the bottleneck?

⚠ Common exam trap

Google Cloud often tests the distinction between metrics that measure performance (latency) versus metrics that measure capacity (utilization, traffic) or errors, leading candidates to mistakenly choose compute utilization or traffic when the question explicitly asks about prediction time.

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 - Endpoint - Prediction latency distribution

The data scientist is investigating slow predictions from a deployed model. The most direct metric to identify the latency bottleneck is the prediction latency distribution, which shows the distribution of response times for online prediction requests. This metric allows you to pinpoint whether the delay is due to model inference time, network overhead, or endpoint queuing, making it the first logical place to inspect.

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 - Model - Compute utilization
Why it's wrong here
Compute utilization covers training and batch resources, not the deployed endpoint's request path. It is the metric to inspect when jobs queue or GPUs saturate during training, but online prediction latency is measured at the endpoint, not on model compute.
✓
Vertex AI - Endpoint - Prediction latency distribution
Why this is correct
Prediction latency distribution reports the spread of response times for online predictions at the endpoint, isolating whether slow inference is the bottleneck. It satisfies the stem's requirement by measuring the deployed model's serving latency directly, rather than CPU, memory or request-count metrics.
✗
Vertex AI - Endpoint - Traffic
Why it's wrong here
Traffic reports request volume reaching the endpoint, showing load rather than response time. It is chosen when diagnosing capacity or quota pressure, but high throughput alone does not reveal where prediction latency is spent, so it cannot isolate the bottleneck.
✗
Vertex AI - Endpoint - Online prediction errors
Why it's wrong here
Online prediction errors counts failed requests, so it surfaces availability or 4xx/5xx problems rather than latency. It is the right metric when predictions fail outright, but the stem describes slow successful responses, which requires a latency metric.

Go deeper

PMLE Practice Question: Refer to the exhibit

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question