# Concepts

**2.1 Creating and Managing Prompts**

RagaAI Catalyst offers a comprehensive Prompt Management System (PMS) that functions like a CMS but specifically for your LLM prompts. Here’s how to get started:

1. **Access the Playground**:
   * From the Catalyst dashboard, navigate to the "Prompt Playground" section.
2. **Create a New Prompt**:
   * Click the `New Prompt` button.
   * Name your prompt descriptively to reflect its purpose or use case.
3. **Craft Your Prompt**:
   * Use the integrated editor with syntax highlighting to write your prompt.
   * Incorporate variables with Jinja templating for dynamic content generation.
4. **Test Prompt**:
   * Run your prompt directly in the Playground to see real-time outputs.
   * Iterate based on the results to refine your prompt.
5. **Save and Version**:
   * Commit your prompt with a detailed message describing any changes.
   * Version control allows you to track improvements and revert if necessary.
6. **Organize Prompts**:
   * Use folders within the PMS to keep your prompts structured and accessible.

**2.2 Prompt Versioning**

Version control in RagaAI Catalyst ensures that you can track and manage the evolution of your prompts. This feature is essential for maintaining high quality and supporting collaborative development.

1. **Automatic Version Assignment**:
   * Each prompt is auto-assigned a version number.
2. **Version History**:
   * Access a complete log of all changes, including commit messages and timestamps.
   * Revert to previous versions if needed.
3. **Set Default Versions**:
   * Designate a default version for each prompt, simplifying deployment and testing.

**2.3 Deleting Prompts**

To keep your workspace clean, RagaAI Catalyst allows you to delete prompts when they are no longer needed.

1. **Locate the Prompt**:
   * In the Playground sidebar, find the prompt you want to delete.
2. **Delete**:
   * Click the three dots (⋮) next to the prompt and select `Delete`.
   * Be aware this action deletes the entire prompt slug, including all versions.


---

# 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/concepts.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.