# Incidents

The Incidents configuration section enables or disables individual machine learning (ML) models that process incoming incident data. These are tenant-level settings that cannot be overridden at the bot or data source level. Access these settings at **Settings > Configuration > Incidents**.

### NLP Classification Model

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Enables Aisera's natural language processing (NLP) classification to analyze incoming incident tickets and predict the most relevant knowledge base articles for each ticket. Aisera surfaces the results as knowledge base recommendations linked to the incident. Enable this when your organization has trained NLP models against your knowledge base and you want to accelerate agent resolution by surfacing predicted content automatically.

{% hint style="info" %}
This setting has no effect unless the TicketIQ entitlement is active for your tenant. 
{% endhint %}

### Sentiment Model

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Attaches a sentiment score to each incoming incident ticket, classifying the ticket's tone as Positive, TendingPositive, Neutral, TendingNegative, or Negative with a confidence score. Enable this when you want to prioritize high-urgency tickets based on tone or to support analytics and reporting on user sentiment trends across incidents.

### Ticket Routing

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

No description Available

### Incident Clustering

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Groups incoming incidents and alerts into predicted clusters, identifying related tickets across your incident data. When **Cmdb Prediction** is also enabled and runs successfully, clustering uses the enriched Configuration Management Database (CMDB) output instead of raw ticket data. Enable this when you want Aisera to automatically identify groups of related incidents, detect recurring problem patterns, or support potential issues management workflows.

{% hint style="info" %}
This setting has no effect unless the AIOps (Potential Issues) entitlement is active for your tenant. 
{% endhint %}

{% hint style="warning" %}
If both **Incident Clustering** and **Incident Clustering v3** are enabled, **Incident Clustering v3** takes precedence and this setting has no effect. Enable only one at a time.
{% endhint %}

See also: [Incident Clustering v3](#incident-clustering-v3)

### Incident Clustering v3

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Groups incoming standard incident tickets into predicted clusters using a second-generation ML algorithm. When **Cmdb Prediction** is also enabled and runs successfully, clustering uses the enriched CMDB output instead of raw ticket data. Enable this when you want to use the newer clustering algorithm instead of the original **Incident Clustering** model. Unlike **Incident Clustering**, this model does not process alert-type tickets.

{% hint style="info" %}
This setting has no effect unless the AIOps (Potential Issues) entitlement is active for your tenant. 
{% endhint %}

{% hint style="warning" %}
If both **Incident Clustering** and **Incident Clustering v3** are enabled, this setting takes precedence and the v1 result is discarded. Enable only one at a time. 
{% endhint %}

See also: [Incident Clustering](#incident-clustering)

### Cmdb Prediction

| **Type**    | Checkbox |
| ----------- | -------- |
| **Default** | Disabled |

Automatically associates each incoming incident ticket and alert with relevant Configuration Items (CIs) from your CMDB, such as services, applications, and devices, based on ticket content. CMDB Prediction runs before clustering models in the pipeline; when **Incident Clustering** or **Incident Clustering v3** is also enabled, those models receive CI-enriched ticket data rather than raw input, improving the quality of cluster groupings. Enable this when your environment has a populated CMDB and you want Aisera to automatically link incoming tickets to the affected services or infrastructure components.

{% hint style="info" %}
 This setting has no effect unless the AIOps (Potential Issues) entitlement is active for your tenant. 
{% endhint %}

See also: [Incident Clustering](#incident-clustering), [Incident Clustering v3](#incident-clustering-v3)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aisera.com/aisera-platform/tenant-setup/aisera-platform-configuration/tenant-configuration-settings/incidents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.