---
sourceDocument: Australia ServiceNow AI Platform Capabilities
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/de-DE/servicenow-platform

 Release :

    - australia

ft:locale :

    - de-DE

ft:publication_title :

    - Australia ServiceNow AI Platform Capabilities

ft:clusterId :

    - platcap

bundleId :

    - platcap

workflow :

    - Platform


---

# Create a model trigger

# Create a MetricBase model
trigger {#ariaid-title1}

* Freigeben Version: Australia
* 
* Aktualisiert 12. März 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 Minuten Lesedauer

Model triggers execute when the time-series data deviates from expected values.

## Vorbereitungen

Role required: admin

## Warum und wann dieser Vorgang ausgeführt wird

There are four model types supported: autoregressive integrated moving average (ARIMA), probabilistic exponentially weighted moving average (PEWMA), Holt-Winters, and seasonal trend decomposition using Loess (STL).  MetricBase  uses the model to create a definition of expected, normal values.

## Prozedur

1. Navigate to AllMetricBaseMetricBase TriggersTrigger Definitions.
2. Select New.
3. On the MetricBase Trigger Creation form, select the Model Trigger option.
4. On the form, fill in the fields.  
   The trigger levels are not initially visible on this form. You configure the
   levels later.
   {#create-metricbase-model-trigger__table_khd_cjn_pbb__entry__2}

   | Field | Description |
   |-|-|
   | Name | Name the model trigger. |
   | Model | Trained model this trigger uses. See [Create and train a predictive model](https://servicenow-prod.fluidtopics.net/TeUvdUo6FKda6ny9G9zyLQ "Use statistical models to determine significant anomalies in real-time using MetricBase triggers. You will need to train a model using representative data that has already been stored in MetricBase."). |
   | Metric | Table metric that you want to monitor. This value is set automatically based on the model, which means you cannot set it yourself. |
   | Table name | Table in the  MetricBase  database that contains the metric that you want to monitor. This value is set automatically based on the model, which means you cannot set it yourself. |
   | Active | Option to activate the trigger. |
   | Description | Description of the trigger. |
   | Spike Direction | Specify whether you want to trigger only on anomalies that occur above predicted values (upward), below predicted values (downward), or both (either). |
   [ ]

   {#create-metricbase-model-trigger__table_khd_cjn_pbb}
5. Select Save.  
   A new record is created.
6. In the MetricBase Model Trigger Levels area on the record you just created, double-click each cell to add values that specify trigger parameters.  
   {#create-metricbase-model-trigger__table_khd_cjn_pbba__entry__2}

   | Column | Description |
   |-|-|
   | Level | Numbers that indicate increasing severity. For example, you might define level 1 to be 2 standard deviations from the mean. Level 2 might be 4 standard deviations. Each level should trigger a different Workflow Studio flow. Level is often used in Condition Scripts. See [Execute triggers conditionally](https://servicenow-prod.fluidtopics.net/WizCHhWwLl0KkDjJVFqIxw "MetricBase triggers execute based on a single metric. Condition Scripts impose additional requirements that determine whether a trigger kicks off a flow."). |
   | Function | Always Greater than or is, meaning that in order to trigger, the time-series metric must be greater than or equal to the number of standard deviations from the mean specified in Number of Standard Deviations. |
   | Number of Standard Deviation | Float value specifying the number of standard deviations the time-series metric must be away from the mean to trigger an alert at this level. |
   [ ]

   {#create-metricbase-model-trigger__table_khd_cjn_pbba}
7. **Wahlweise:** Add rows to the table to create multi-layered triggering behavior.  
   Typically, each additional row (level) indicates a more severe condition. The Workflow Studio flow associated with the level should warn with increasing severity.
8. Select Update.
9. **Wahlweise:** Add a triggering condition that determines whether a trigger executes a Workflow Studio flow.  
   See [Execute triggers conditionally](https://servicenow-prod.fluidtopics.net/WizCHhWwLl0KkDjJVFqIxw "MetricBase triggers execute based on a single metric. Condition Scripts impose additional requirements that determine whether a trigger kicks off a flow.").
10. Test your model and trigger on real data before deploying to production.
{#create-metricbase-model-trigger__steps_yjd_rgq_zgb}

## Model Trigger form {#create-metricbase-model-trigger__example_bct_z1y_ytb}

## Nächste Maßnahme

Associate this trigger with a Workflow Studio flow. For more information, see [Assign a trigger to a flow](https://servicenow-prod.fluidtopics.net/vsq69MLtx2Gtg1FT3WVbow "Now that you created a trigger, use Workflow Studio to specify the flow a trigger executes. The flows can provide alerts for unexpected behavior.").