> For the complete documentation index, see [llms.txt](https://docs.nexthink.com/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nexthink.com/platform/user-guide/search-and-workspace/understanding-nexthink-assist.md).

# Understanding Nexthink Assist

Nexthink Assist is an AI model operated by Nexthink within the Nexthink AWS environment. It can answer any questions about Nexthink, Digital Experience, and your IT environment, as well as streamline campaign creation:

* **Ask about Nexthink:** Get quick answers about Nexthink features, workflows, and configurations.
* **Analyze data:** Extract and compile data, delivering instant insights on device performance, binaries, user sessions, and application details. Nexthink Assist intelligently queries multiple sources to provide accurate, contextual answers. These include Nexthink documentation, Infinity configuration objects (such as live dashboards and library packs), and NQL data.
* **Create IT campaigns:** Describe your objective in plain language, and Nexthink Assist generates a campaign draft. You can then refine, preview, and save it directly to the Campaigns module.

{% hint style="warning" %}
The system displays the ✦ sparkles icon to indicate AI-generated content or insights.

**Nexthink Assist** is continually improving. As it evolves, it may occasionally provide information that requires verification. Nexthink recommends confirming your results to ensure accuracy.
{% endhint %}

Refer to the [Nexthink Assist AI model card](https://docs.nexthink.com/legal/global-ai-hub/nexthink-assist-ai-model-card) documentation for more information on how it operates and processes data.

## How Nexthink Assist works

Nexthink Assist follows an iterative process:

1. Forms an initial hypothesis and selects tools.
2. Gathers and analyzes data.
3. Decides whether further data is needed.
4. Repeats if necessary to enrich the output.
5. Presents a concise response.

When Nexthink Assist provides responses, it generates a **Sources** section at the bottom, which contains embedded links such as NQL queries, documentation pages, and investigation results.

## Nexthink Assist data scope when creating NQL queries

Nexthink Assist provides accurate and relevant answers across all current data domains, including newly released features and dynamic data.

This includes:

* Data Nexthink collects through the standard [Nexthink NQL data model](/platform/understanding-key-data-platform-concepts/nql-data-model.md).
* Custom device or user classification, configured through [Device and user classification](/platform/user-guide/administration/system-configuration/data-management/environment/product-configuration.md).
* Manual custom fields configured through [Custom fields management](/platform/user-guide/administration/content-management/custom-fields-management.md).
* Specific [remote action](/platform/user-guide/remote-actions/using-remote-actions/monitoring-remote-actions-execution-statistics.md) inputs and outputs.
* Specific [campaign](/platform/user-guide/campaigns/working-with-campaigns/monitoring-specific-campaign-responses.md) responses.

{% hint style="warning" %}
Nexthink Assist does not currently support query-based and rule-based custom fields, custom ratings, and custom trends.

If a question references unsupported data, Nexthink Assist will either fail to produce a valid query or generate a plausible-looking but incorrect one.
{% endhint %}

Refer to [Analyzing your environment with Workspace](/platform/user-guide/search-and-workspace/using-workspace/analyzing-your-environment-and-troubleshooting-it-incidents.md) for more guidelines.

***

RELATED TOPICS

* [Workspace](/platform/user-guide/search-and-workspace.md)
* [Using Workspace](/platform/user-guide/search-and-workspace/using-workspace.md)
* [Configuring Workspace](/platform/user-guide/search-and-workspace/configuring-workspace.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.nexthink.com/platform/user-guide/search-and-workspace/understanding-nexthink-assist.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.