ZBrain Documentation
  • ZBrain Documentation
    • ZBrain XPLR
      • ZBrain XPLR modules
      • Get started with ZBrain XPLR
      • Simulation XPLR
        • AI solutions library
      • Taxonomy XPLR
      • Solution XPLR
      • Portfolio XPLR
      • Functional Design XPLR
    • ZBrain Builder
      • Components of ZBrain Builder
      • 📚Knowledge base
        • How to create a knowledge base?
        • Knowledge source
        • Information schema
        • File summary
        • Automated reasoning
        • Retrieval testing
        • Knowledge base settings
      • 📱App
        • How to create a new app?
          • How to leverage knowledge base for app creation
          • How to build advanced applications using Flow
        • How to set up and customize your app?
        • How to access the app reporting dashboard?
      • 🤖ZBrain AI agents
        • Get started with agents on ZBrain Builder
        • Deploying pre-built agents
        • Creating custom AI agents
          • Agent setup
          • Define input sources
          • Define Flow
            • Key elements of a Flow
            • Flow Components
              • AITable
              • Airtable
              • Amazon S3
              • Amazon SNS
              • Amazon SQS
              • Amazon Textract
              • Apify
              • Apollo
              • Approval
              • Asana
              • Azure Communication Services
              • Azure Cosmos DB
              • Azure Document Intelligence
              • Azure OpenAI
              • Azure Translation
              • Bannerbear
              • Baserow
              • Beamer
              • Bedrock Claude
              • Bettermode
              • Binance
              • Bing Search
              • Blackbaud
              • Bonjoro
              • Box
              • Brevo
              • Brilliant Directories
              • Bubble
              • CSV
              • Calendly
              • Certopus
              • Clearout
              • Clockodo
              • Code
              • Confluence
              • Connections
              • Constant Contact
              • Contiguity
              • Contentful
              • Customer.io
              • Crypto
              • Databricks
              • Data Mapper
              • Date Helper
              • DeepL
              • Delay
              • Discord
              • Discourse
              • Drip
              • Dropbox
              • Dust
              • Facebook Pages
              • Figma
              • Files Helper
              • Flowise
              • Flowlu
              • Formbricks
              • Frame
              • Freshdesk
              • Freshsales
              • GCloud Pub/Sub
              • GenerateBanners
              • GhostCMS
              • GitHub
              • GitLab
              • Gmail
              • Google Calendar
              • Google Contacts
              • Google Docs
              • Google Drive
              • Google Forms
              • Google Gemini
              • Google My Business
              • Google Search
              • Google Search Console
              • Google Sheets
              • Google Tasks
              • Groq
              • Hacker News
              • Heartbeat
              • HubSpot
              • HTTP
              • Image Helper
              • Inputs
              • Instagram for Business
              • Intercom
              • Invoice Ninja
              • Jira Cloud
              • Jotform
              • Kimai
              • Kizeo Forms
              • LeadConnector
              • Line Bot
              • Linear
              • LinkedIn
              • LinkedIn Actions
              • LLMRails
              • Lusha
              • MailerLite
              • Mailchimp
              • Mautic
              • Microsoft Dynamics 365 Business Central
              • Microsoft Dynamics CRM
              • Microsoft Excel 365
              • Microsoft OneDrive
              • Microsoft Outlook Calendar
              • Microsoft Teams
              • Mixpanel
              • MongoDB
              • Notion
              • Odoo
              • OpenAI
              • OpenRouter
              • Pastebin
              • PDF
              • Postgres
              • PostHog
              • Pushover
              • Qdrant
              • Queue
              • Razorpay
              • Router
              • Salesforce
              • SendGrid
              • ServiceNow
              • SFTP
              • SharePoint
              • Slack
              • SMTP
              • Snowflake
              • SOAP
              • Spotify
              • Stability AI
              • Stable Diffusion Web UI
              • Storage
              • Stripe
              • SurrealDB
              • SurveyMonkey
              • Taskade
              • Telegram Bot
              • Text Helper
              • Trello
              • Twilio
              • Twitter
              • Utilities
              • WhatsApp Business
              • WordPress
              • XML
              • YouTube
              • ZBrain
              • Zendesk
              • ZeroBounce
              • Zoho Books
              • Zoho CRM
              • Zoho Invoice
              • Zoom
            • How to Define a Flow?
            • How to Test Each Step in the Flow?
          • Configure Additional Settings
          • Test and Deploy Agents
          • How to access, monitor, and manage agent performance and tasks?
      • 💻Prompts
        • How to create a prompt
        • How to manage and monitor prompts
        • How to manage prompt versions and restore previous versions
        • User management: How to assign prompt permissions?
      • 📺Monitor
      • 🔐Security features
      • Settings
      • 📖API tutorials
        • 📚Knowledge base
          • Automated reasoning
        • 📱APP
        • 🤖Agents
Powered by GitBook
On this page
  1. ZBrain Documentation
  2. ZBrain Builder
  3. Prompts

How to create a prompt

PreviousPromptsNextHow to manage and monitor prompts

Last updated 11 hours ago

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.

💻