# Create with AI using Prompt Wizard

Creating good system prompts from scratch can be tricky - it requires a structured explanation of the inputs, methodology, and expected outputs. In the absence of a base system prompt, it might be difficult to get started and move on to iterative improvement. 

This is solved on RagaAI Catalyst using a built-in Prompt Wizard within the Playground.

<figure><img src="/files/12hNSvFThaopzFIvdpPx" alt=""><figcaption></figcaption></figure>

From any prompt box (System, User, etc), users can click the wand icon highlighted above, and gain access to a chat sidebar for AI help. In the sidebar, users can chat with the LLM of their choice (using a dropdown) and provide instructions in natural language.

<figure><img src="/files/w7ehFo6R2KiXaNel0A0f" alt=""><figcaption></figcaption></figure>

Users can go back-and-forth with the LLM, outlining improvements and additions after reviewing each response.

<figure><img src="/files/wb8IfpgGC0aRWnEf7GZw" alt=""><figcaption></figcaption></figure>

Once a system prompt feels good to begin with, they can click the "Use this response" button against the respective chat entry to place it back in the starting box.

<figure><img src="/files/C4ZDnfjcLhhXv34fd1fU" alt=""><figcaption></figcaption></figure>

**Note:** Users can also refine base prompts by typing into the prompt boxes and then clicking the wand icon. This will automatically attach the pre-written prompt into the chat context for further improvement.

<figure><img src="/files/fI09aEreKHzIWRDrmkaG" alt=""><figcaption></figcaption></figure>


---

# 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.raga.ai/ragaai-catalyst/prompt-playground/create-with-ai-using-prompt-wizard.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.