# MOTAR AI Engine

{% hint style="warning" %}
**MOTAR AI Engine** with zero trust orchestration layer (beta)  is in early development and may produce incorrect or incomplete information.
{% endhint %}

**MOTAR AI Engine** with zero trust orchestration layer (beta) is now packaged with every MOTAR Instance!\
It automatically **learns** from your uploaded assets to provide contextual answers and insights, while continuing to **respect** all asset **permissions**.\*

<figure><img src="https://540871446-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FVJV84grXWXSLppsAzVKx%2Fuploads%2FoUcSdw2sCHU1KuVFsDML%2Fimage.png?alt=media&#x26;token=19b59626-59db-444b-b8c8-88ed62b8006f" alt=""><figcaption></figcaption></figure>

*To install* **MOTAR AI Engine** with zero trust orchestration layer *(beta) on your instance, follow the guide:* [#ai-beta-installation](https://docs.motar.com/welcome/getting-started/production-installation/advanced-deployment-guide#ai-beta-installation "mention")

*\*Currently AI compatible assets do not include 3D models or Apps.*

#### Searching for Assets by Tag

The MOTAR AI chat supports natural language tag queries. Use any of the following patterns to find assets:

**Find assets with a specific tag:**

* `Show me assets`` `**`tagged`**` ``with training`
* `Find items with the`` `**`tag`**` ``safety`
* `What assets have a`` `**`tag`**` ``of onboarding?`
* `Do I have anything`` `**`tagged`**` ``maintenance?`

**Browse or audit your tags:**

* `Do I have any`` `**`tagged`**` ``items?`
* `What`` `**`tags`**` ``are on my assets?`
* `How many`` `**`tagged`**` ``items do I have?`
* `Show me items with`` `**`tags`**

**Tips:**

* Tag names are **not** case-sensitive — `Safety` and `safety` work the same.
* Tags with hyphens or dots are supported — e.g., `tagged with safety-vest` or `tag of v1.2`.
* Quotes around the tag name are optional — `tag "onboarding"` and `tag onboarding` both work.
* The query just needs to include a recognizable tag phrase followed by your tag name — phrasing doesn't have to be exact.

**What won't work:**

* Very short or ambiguous phrasing like `find safety` (no tag keyword) — include words like *tagged*, *tag*, or *items with tag* to trigger tag search.


---

# 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.motar.com/additioinal-features/motar-ai-engine.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.