> For the complete documentation index, see [llms.txt](https://docs.moonlander.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.moonlander.ai/v.1.0.0.alpha-4/fundamentals/getting-set-up/promptabletemplate.md).

# PromptableTemplate

While the [Generator Stack Presets](/v.1.0.0.alpha-4/fundamentals/getting-set-up/generator-stack-presets.md) look very pretty, the real fun is making your own custom worlds of course! The easiest way to get started with your custom worlds is with the **PromptableTemplate**, as it is already preconfigured to listen to your text prompts. Besides that, the generator settings are set in a default way that works well with different types of terrains.

With the PromptableTemplate you can load assets through the text prompting interface. By typing a list of assets that you would like to see, Shapeshifter will create generators (and terrains) that will resemble your input.

{% hint style="info" %}
As of now, prompting works only for loading the right assets! **V1.0.0-alpha.5 will contain much more sophisticated prompting**, like creating the generator settings as well. Please stay tuned!
{% endhint %}

## Getting Started

First, make sure your asset library has the type of assets that you are looking for. You can also wait for the terrain to generate, but **if you prompt palm trees without having them in your library, you won't see any**. Luckily, the BoosterPack will consists of a good variety of assets to start out with. 

{% hint style="info" %}
You can also use your own assets of course. In that case, make sure the assets have the right metadata by using our [Asset Tagging](/v.1.0.0.alpha-4/explore-topics/library/asset-tagging.md). 
{% endhint %}

Now, let's get generate your first custom world! You can follow this example to see how it works:

<details>

<summary><strong>Step 1: Load the BoosterPack library in Shapeshifter and select the</strong> PromptableTemplate <strong>in the Generator Stack</strong></summary>

<img src="/files/cJJixbwx6F3IuOuBDHLN" alt="" data-size="original">

In the Shapeshifter **Setup**, select in **Library** the **BoosterPack**. Then, press **Edit Generators** if you don't have the Generator page in view. Then, select the **Generator Stack** and select the **PromptableTemplate** in the list:

<img src="/files/FJzO0seXgPRqppJo2bv9" alt="" data-size="original">

</details>

<details>

<summary>Step 2: Write a prompt to load assets, like "Cacti, meadow, sunny, mushrooms, giant rock<strong>"</strong> </summary>

<img src="/files/xJ1YHfsnWNxw1HgByy7I" alt="" data-size="original">

</details>

<details>

<summary>Step 3: Press Generate Area and create your terrain!</summary>

Shapeshifter will now look through your **Asset Library** to find related assets and spawn them.

</details>

## Inspecting your new generator

<figure><img src="/files/UWsBOcsIk0kLYycn4k6l" alt=""><figcaption><p>A world generated with the prompt: "Cacti, meadow, sunny, mushrooms, giant rock<strong>".</strong></p></figcaption></figure>

Now that your world is generated, you can start iterating your world by inspecting the generators. This will give you insights in which assets were loaded, and allow you to change the scene a bit. The **PromptableTemplate** have a few generators loaded, and several of them have an asset loader in place.  Let's take a look of a few of them:

### ObjectPlacementGenerator

The Flowers generator is an ObjectPlacementGenerator responsible for finding flowers. As you can see, the generator has found several cacti to place! The same goes for the Scattered Objects Generator, both mushrooms and rocks were found.

<div><figure><img src="/files/sebmRgolUwlD9jTqXIOa" alt="" width="301"><figcaption><p>Flowers generator</p></figcaption></figure> <figure><img src="/files/xRmbFZpoZNcQpbf9T3aH" alt="" width="196"><figcaption><p>Scattered Objects generator</p></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 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.moonlander.ai/v.1.0.0.alpha-4/fundamentals/getting-set-up/promptabletemplate.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.