How to create a prompt

Creating a prompt in ZBrain is an easy process that allows you to guide your AI application’s responses with precision. Follow the steps below to create and configure a prompt effectively:

Step 1: Initiate prompt creation

• Navigate to the right side of the prompt manager interface.

• Click the ‘Create’ button to initiate the process of creating a new prompt.

• Once clicked, a new panel will open for you to begin configuring the prompt.

Step 2: Configure prompt details

In the prompt panel:

Provide a clear title

• Enter a title: Provide a clear and descriptive name for your prompt. Click the ✏️ (pencil) icon to edit the title.

Select the model and provider

• Choose the appropriate AI provider (e.g., OpenAI, Claude AI) from the dropdown menu.

• Select the specific model you want to use (e.g., GPT-4, Claude 2).

• Click the settings (⚙️) icon next to the model selection to configure parameters like temperature, max tokens, and top-p values etc.

Static prompt type: System (predefined)

System is the default and static prompt type.

• The system message defines instructions that guide the model's behavior or tone throughout the session.

• This setting is predefined and cannot be manually selected, but automatically applies to the conversation.

Add roles

• Click ‘+ Message’ to define different roles in your prompt structure. Select the prompt type based on your use case:

  • User: Represents the user’s query or interaction input.

  • Assistant: The model’s response to the user’s input.

Step 3: Add instructions

You have two options for entering the prompt instructions that will guide the model:

Option 1: Manual entry

• Type the prompt instructions directly into the text field.

• These instructions can include detailed tasks, specific formatting rules, tone guidelines, etc.

Option 2: Auto-generate using LLM

• Click the ‘Generate’ button to automatically create instructions using a large language model.

• A dialogue box will appear titled ‘What would you want to update?’

Within this box, you can:

• Create a new prompt: Describe the function or output you want the AI solution to perform (e.g., “Summarize long documents in bullet points”).

• Optimize an existing prompt: Paste an existing prompt you'd like to refine or improve using AI suggestions.

• After entering your input or requirements, click ‘Create’ to generate the prompt.

• Review and update the generated instructions as needed.

Step 4: Define input variables

Variables allow you to dynamically insert values into prompts at runtime. This approach supports reusability and flexibility in prompt behavior.

Option 1: Add variables using the interface

1. Click ‘+ Add’ to define variables.

1. Select from the following predefined variable types:

   • App:

     • ID, Name, Description

   • Flow:

     • ID, Name

   • User:

     • ID, Name, Email

   • Time and date:

     • Current date and time, Day, Timezone

   • Session:

     • ID, query, context, feedback, input files

Option 2: Add dynamic placeholders in text

• Use curly brackets {{}} to add dynamic placeholders directly into your prompt.

• These placeholders are populated with actual values at runtime.

Example:

"Summarize the following content: {{content}}"

• The {{content}} variable will be replaced by the actual input content when the prompt is executed.

This enables the same prompt to be reused across different scenarios.

Step 5: Publish the prompt

After configuring all necessary settings:

1. Review your prompt instructions, variables, and roles.

2. Click the ‘Publish’ button to save and activate your prompt.

3. The prompt is now ready for use in your apps.

Step 6: Test the prompt

Testing is crucial to ensure the prompt works as intended and yields the desired outputs.

Enter a test query

• Input sample data or a query that the AI should respond to. This query should represent real-world input that your AI will handle.

• Click ‘Run Prompt’ to execute the configured prompt and generate output based on the provided input.

Review the response

• Analyze the output.

• If needed, refine:

  • Instructions

  • Model settings

  • Roles or variables

Iterate and improve

• Test multiple scenarios or input variations to ensure the prompt works consistently.

• Based on testing, return to the configuration panel to make further adjustments.

• After making changes, republish the prompt and retest until the desired performance is achieved.

By following these steps, you can easily create high-quality, structured prompts that align with your application’s goals and ensure consistency across AI interactions.