# Basic Prompt Structure

Prompts are what makes your generations work. The prompt may look like this:

An oil painting | of a Dwarf warrior, | with (red) hair, holding a sword, | Surrealism, | dark, moddy, | by Rembrant

<figure><img src="https://2463013151-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FrjzSinvVPe17AZtDte0Z%2Fuploads%2FdsjfxiAg0kwcbr39M9Kw%2F00694_An_oil_painting_of_a_Dwarf_warrior_with_red_hair_holding_a_sword_Surrealism_dark_moddy_by_Rembrant_seed_3896763499.png?alt=media&#x26;token=f58f348a-fdaf-40a4-a891-dbccc837be14" alt="A red haired short woman holding a sword. "><figcaption></figcaption></figure>

Lets break this down.

"An oil painting" is the Art Medium you want.&#x20;

"of a Dwarf Warrior" this is subject of your prompt.

"with (red) hair, holding a sword" are features of your subject. The () increases the weight of red in your prompt.

"surrealism" is the art style.

"dark, moody" are the attributes describing the Art. This can also be stuff like god rays and volumetric lighting.

"by rembrant" is an artist, which style we are trying to copy.

All of these will be explained in the following chapters.&#x20;

{% tabs %}
{% tab title="Euchale's Note" %} <img src="https://2463013151-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FrjzSinvVPe17AZtDte0Z%2Fuploads%2FgDMk7omYGMFfS9i6sc4E%2Fimage.png?alt=media&#x26;token=d48b5a5a-f308-4688-9ac4-27e5d78d91d2" alt="" data-size="line"> If you want to see how to create to a prompt kind of like this and see me struggle, you may watch this video: <https://www.youtube.com/watch?v=KCSQcsXgcLk>
{% endtab %}
{% endtabs %}


---

# 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://artroomai.gitbook.io/local_tutorials/resources/prompting-tutorials/basic-prompt-structure.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.
