> For the complete documentation index, see [llms.txt](https://docs.icraft.design/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.icraft.design/editor-features/resource-panel/asset-library/ai-asset-recommendation.md).

# AI Asset Recommendation

**AI Asset Recommendation** is an intelligent assistant feature within the iCraft Asset Library.

With just **one natural language description** of the scene you want to build or the models you need, the system will automatically search and recommend a set of matching 3D assets.

It is not just a search tool, but a “scene designer” that understands your intent. By interpreting your description, the AI can recommend a complete set of scene elements that fit your creative idea.

***

## Value of AI Asset Recommendation

* **Intelligent Search**\
  Describe your needs in natural language and instantly receive a list of candidate assets, eliminating the need for manual searching.
* **Smart Asset Combinations**\
  The AI recommends assets based on scene semantics. For example, describing a “living room” may generate suggestions such as sofas, coffee tables, TV cabinets, carpets, and floor lamps.
* **Batch Operations**\
  You can select multiple assets at once, purchase them together, and place them into the scene with a single action.
* **Flexible Layout**\
  Both free assets and point-based assets can be selected together. After placement, you can still adjust materials, scale, and position to further refine your design.

***

## How to Use AI Asset Recommendation？

{% stepper %}
{% step %}

#### Open the Asset Library

Open the **Asset Library** and switch to the **“AI Recommend”** tab.
{% endstep %}

{% step %}

#### Describe Your Scene

Enter a **natural language description** in the input field.

Example:：\
`I want to create a modern Nordic-style living room that includes a three-seat sofa, a coffee table, a TV cabinet, a floor lamp, and a carpet`
{% endstep %}

{% step %}

#### Wait for the AI Recommendations

The system will automatically generate a set of recommended assets based on your description.
{% endstep %}

{% step %}

#### Select the Assets

Choose the assets you want from the recommendation list. You can select individual assets or select all.
{% endstep %}

{% step %}

#### Click “Add”

Click **Add** to enter the confirmation page. The confirmation page will display number of selected models, number of models to obtain, and total credits required.\
You can also choose the placement layout: `Grid layout(default)`/ `Linear layout`
{% endstep %}

{% step %}

#### Confirm and Place

After clicking **Confirm**, the system will automatically consume credits to purchase and place all selected models onto the canvas in one go, according to the chosen layout. You can then adjust their position, scaling, and materials on the canvas.
{% endstep %}
{% endstepper %}

<figure><img src="/files/rXHBqJZ0UHotrPNDGdkl" alt=""><figcaption></figcaption></figure>

***

## How to Get More Accurate Recommendations?

To obtain more relevant recommendations, try including the following elements in your description:

* **Scene Type**\
  Examples:\
  \&#xNAN;*`living room / office / wind power generation process / thermal power plant / park / large language model architecture diagram`*
* **Style (optional)**\
  Examples:\
  \&#xNAN;*`Nordic / modern / industrial / minimal / yellow-black / blue-white`*
* **Key Elements (optional)**\
  Examples:\
  \&#xNAN;*`three-seat sofa / coffee table / TV cabinet / sun / cooling tower / workshop / fountain / server`*
* **Color or Material Preferences (optional)**\
  Examples:\
  \&#xNAN;*`gray fabric / natural wood / metal / leather / glass`*
* **Usage Scenario (optional)**\
  Examples:\
  \&#xNAN;*`presentation / engineering visualization / lightweight mobile display`*

#### Example Prompts

**Example 1**\
`“I want to create a small Nordic-style living room with a three-seat sofa, a coffee table, a TV cabinet, and a floor lamp, with gray and white tones.”`

**Example 2**\
`“I want to build a refinery scene that includes crude oil storage tanks, refining towers, oil transport ships, and tanker trucks, with a unified color style.”`


---

# 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.icraft.design/editor-features/resource-panel/asset-library/ai-asset-recommendation.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.