Create a Prompt

​

Creating a New Prompt

Create prompts through the platform’s visual editor.

​

1. Create a Prompt

Open the create menu to start creating a new prompt.

​

2. Name Your Prompt

Give your prompt a descriptive name and choose the generation type. Generation Types: Each type has specific tags available: Text - Conversational AI and content generation

• <System> - System-level instructions
• <User> - User message
• <Assistant> - Assistant message

Object - Structured JSON with schema validation

• <System> - System-level instructions
• <User> - User message
• <Assistant> - Assistant message

Image - Visual content generation

• <ImagePrompt> - Image prompt description

Speech - Text-to-speech audio

• <SpeechPrompt> - Text to speech input
• <System> - System-level instructions

Learn more about generation types →

​

3. Write Your Prompt

Select your model and write your prompt using message tags. Available models depend on your platform configuration. Common options include GPT-4, Claude, Gemini, and more.

​

4. Run your Prompt

Add your input variables and run the prompt to see results.

​

5. Publish Your Prompt

Publish to save your changes.

​

Next Steps