19.1 Configuring Model Monitoring on Agent Platform

Key Takeaways

  • Model Monitoring v1 is generally available and configured on Agent Platform endpoints, while Model Monitoring v2 (preview) attaches a model monitor to a model version in Model Registry.
  • Model Monitoring v2 supports tabular models served on Agent Platform or elsewhere, including GKE and BigQuery, through reference models.
  • Model Monitoring v1 monitors every feature with a default alert threshold of 0.3 and runs every 24 hours by default, with a minimum granularity of 1 hour.
  • Endpoint-based monitoring needs request-response logging, so private endpoints using VPC Network Peering can't be monitored this way.
  • Monitoring v2 compares a target dataset with a baseline dataset using a time window and optional offset, and it can run on demand or on a schedule.
Last updated: September 2026

The exam guide lists configuring and using Model Monitoring on Gemini Enterprise Agent Platform to establish continuous evaluation metrics for production models. Monitoring catches silent failures: the endpoint is healthy and fast, but predictions are getting worse because the data changed.

Two Offerings

AspectModel Monitoring v1 (generally available)Model Monitoring v2 (preview)
Attached toAn Agent Platform endpoint (monitoring job per endpoint)A model version in Model Registry (a model monitor per version)
Where the model runsAgent Platform endpointsAgent Platform or other infrastructure (GKE, BigQuery, and others) through reference models
Model typesTabular AutoML and imported tabular custom modelsTabular models
DetectionTraining-serving skew (needs training data) and prediction driftInput feature drift, output inference drift, feature attribution changes, against any baseline
When to chooseProduction-level support for an endpoint-deployed modelAll other cases. Google says v2 has all v1 capabilities and more

v1 users don't have to migrate. Both versions can run side by side during a transition.

Model Monitoring v1 on an Endpoint

  1. Ensure all models on the endpoint are tabular AutoML or imported tabular custom models.
  2. For skew detection, provide the training dataset (Cloud Storage or BigQuery) and the target field. For drift detection, training data isn't required.
  3. For custom models, provide an analysis instance schema (the job waits in pending until it has one).
  4. Configure:
    • Alert thresholds per feature. The default is 0.3 for every feature. For example, Age=0.4 alerts when Age's distribution distance exceeds 0.4.
    • Sampling rate of logged prediction requests (all requests by default).
    • Monitoring frequency: 24 hours by default, 1 hour minimum.
    • Notifications: email and Cloud Monitoring channels (the console supports PagerDuty, Slack, and Pub/Sub).

Model Monitoring v2 Building Blocks

1. Register the model

Register it in Model Registry. For models served elsewhere, register a reference model (a placeholder name without artifacts). Reference models can't use feature attribution monitoring.

2. Create a model monitor (one per model version)

  • Schema: feature fields, prediction fields, and optional ground-truth fields, with data types and repeated for arrays. AutoML Tables schemas are fetched automatically.
  • Defaults: objectives, training dataset, output location, and notification settings. Jobs use these unless overridden.
  • Output: a Cloud Storage location. The monitoring service agent needs write access, or the service creates a default bucket.

3. Choose data sources

SourceNotes
BigQuery table or queryNeeds a timestamp column (timestamp_field) for time windows and continuous monitoring. Partition by timestamp for cost and speed
Cloud StorageCSV (with header) or JSONL
Batch inference jobMonitoring runs soon after the batch job completes
Endpoint request-response loggingRequires logging enabled. Tables include logging_time. Private (VPC peering) endpoints aren't supported because they don't log requests
Managed datasetTabular dataset format

Nested features aren't supported, so flatten them first. Array columns are flattened into individual values.

4. Define baseline and target

  • Baseline: a reference, usually the training dataset or an earlier production window.
  • Target: recent data to compare.
  • Time specification: a start and end time range, or a window plus offset. For example, the target is the last 24 hours, and the baseline is the same 24 hours one week earlier.
  • Larger windows reduce noisy alerts caused by small sample sizes.

5. Select objectives and thresholds

ObjectiveMetrics
Input feature data driftCategorical: L-infinity or Jensen-Shannon divergence. Numerical: Jensen-Shannon divergence
Output inference data driftSame metrics, applied to predictions
Feature attributionSHAP values, tracking changes in each feature's contribution

6. Run and schedule

Run on-demand jobs or scheduled runs for continuous monitoring. Scheduled runs with time specifications support BigQuery and endpoint logging sources. Model Monitoring v2 itself isn't charged while in preview, but you still pay for the BigQuery, Cloud Storage, and batch inference it uses.

Monitoring When Ground Truth Arrives

Distribution monitoring is a proxy. When labels arrive, measure real performance:

  1. Store predictions with a request ID and timestamp (endpoint logging or batch output).
  2. Join them with ground truth in BigQuery when outcomes are known.
  3. Run the model evaluation component on recent windows in a scheduled pipeline, and compare with the validation baseline (Chapter 7).
  4. Alert on performance drops, sliced by key segments.

From Alerts to Action

AlertTypical response
Skew on key features right after launchCheck preprocessing parity and feature pipelines (Chapter 15)
Gradual drift over weeksInvestigate the cause. Retrain on recent data if accuracy is affected
Prediction drift with stable inputsPossible concept change or an upstream label or business change. Check outcomes
Attribution shift for an important featureLook for broken or changed feature definitions

Route alerts to Pub/Sub so a Cloud Run function can open incidents or trigger a retraining pipeline where the policy allows (Chapter 17).

Test Your Knowledge

A company serves a tabular model on GKE, not on Agent Platform, and wants managed drift monitoring of its logged predictions in BigQuery. What should it use?

A
B
C
D
Test Your Knowledge

A team enables Model Monitoring v1 on an endpoint without changing any settings. How often do monitoring jobs analyze logged inputs, and what alert threshold applies to each feature?

A
B
C
D
Test Your Knowledge

A bank wants Model Monitoring based on endpoint request-response logging, but its model is on a private endpoint that uses VPC Network Peering. What is the issue?

A
B
C
D