# Segments

Segments are saved filters on [Log](https://docs.dbnl.com/workflow/logs) data corresponding to a specific behavioral signal discovered manually or from an [Insight](https://docs.dbnl.com/workflow/insights).

All Segments are computed and published to the [Segments Dashboard](https://docs.dbnl.com/dashboards#segments-dashboard) as part of the [DBNL Data Pipeline](https://docs.dbnl.com/configuration/data-pipeline) and adapt future analytics by informing DBNL that the saved Segment is a meaningful bifurcation of the [Logs](https://docs.dbnl.com/workflow/logs) data.

## When to Create Segments

Create a segment when you've identified a meaningful behavioral pattern you want to track over time, such as:

* **Error conditions**: Logs containing specific error types or failure patterns
* **High-value interactions**: User sessions with purchases, conversions, or key actions
* **Quality issues**: Low-scoring responses that need monitoring
* **User cohorts**: Specific user groups (power users, new users, etc.)
* **Performance bottlenecks**: Requests exceeding latency thresholds
* **Experiment cohorts**: Specific [experiment variants](https://docs.dbnl.com/logs#experiment-filters) for comparing configurations (e.g., model A vs model B)

Once saved, segments are automatically analyzed in future pipeline runs, generating dedicated metrics and appearing on dashboards.

## Creating Segments

Segments can be created in three ways:

1. From an [Insight](https://docs.dbnl.com/workflow/insights) that specifies a Segment corresponding to the behavioral signal observed
2. Anywhere a filter is constructed on the [Explorer](https://docs.dbnl.com/workflow/explorer) or [Logs](https://docs.dbnl.com/workflow/logs) pages
3. Manually from the Segments page on the sidebar

Segments can be modified or deleted from the Segments page on the sidebar.

<figure><img src="https://content.gitbook.com/content/yx9NXaWRjaOtW8ILLJQO/blobs/KiNYBYSd7sYdbSik8eAx/image.png" alt=""><figcaption></figcaption></figure>


---

# 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.dbnl.com/workflow/segments.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.