> For the complete documentation index, see [llms.txt](https://academy.shade.inc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.shade.inc/ai-tools/ai-search-best-practices.md).

# AI Search Best Practices

You can find the media you are looking for faster with an AI search. To AI search anything in your drive, press **`cmd/ctrl + k` .** To AI search your current folder, press **`cmd/ctrl + f` .**

{% embed url="<https://youtu.be/v4_6VhK9xPM?si=ozQd6Gguks7zEOwr>" %}

{% embed url="<https://youtu.be/XZsCK2YPbn0?si=iKV5IKgBg0S8MPJW>" %}

<figure><img src="https://450378260-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUNq6h2Bfw7aAK0J2ffnZ%2Fuploads%2FvfgYoXp8nrzjzlUI2GUX%2FAISearch.gif?alt=media&#x26;token=f4255333-65eb-4094-b74e-2aa8d9cbd31f" alt=""><figcaption></figcaption></figure>

Shade’s AI is not centered around tags; it’s centered around creating a unified understanding of assets (the core unit of information) and text (how we typically search). Tags are only a mere snapshot of this with 1500 words that we’ve curated while creating Shade. It is not representative of every image or frame, nor does it capture semantic information such as actions etc.

DO: “Drone footage of a forest in the autumn on a mountain”

DON’T: “Forest, Trees, Drone”

DO: “Bottles on a shelf”

DON’T: “Shelf, Bottle”

After you have completed an AI search, you will want to choose the type of asset you are searching for by selecting the asset type below your query.

{% hint style="info" %}
To exclude a folder from being indexed by AI or appearing in AI searches, you can right click on any folder and press “Exclude folder from AI”

To see which folders are excluded or add one back, open the drive's menu in the sidebar, choose **View AI Excluded Folders**, and click **Add back to index** next to the folder.
{% endhint %}

{% embed url="<https://youtu.be/lIWWwSTWYQw?si=UQMBO1EQ744zTR2E>" %}

<div data-full-width="false"><figure><img src="https://450378260-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FUNq6h2Bfw7aAK0J2ffnZ%2Fuploads%2FnP7ivb36h5sz6yYQXvpI%2FScreenshot%202025-02-16%20at%2017.59.27%402x.png?alt=media&#x26;token=0f1eb188-cf5b-498d-8b3c-1fa6a6213766" alt=""><figcaption></figcaption></figure></div>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://academy.shade.inc/ai-tools/ai-search-best-practices.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
