Stammer.ai Docs
  • Welcome
    • 👋Welcome to Stammer.ai
    • 📑About Stammer.ai
    • 🆕New/ Latest Updates
  • START HERE
    • ❓What is Stammer.ai?
    • 🫡Agency Quick Start Guide
    • 📚Glossary
    • 🤑Our Community
  • AI Features
    • 🤖AI Agents (Chatbots)
      • How AI Agents Work
      • How to Build an AI Agent
    • 🔃AI Agent Dashboard
      • (White Label) Marketplace
      • Default Chatbot
      • Share Chatbot
      • Clone Chatbot
      • Chatbot UUID
      • Delete Chatbot
      • Summary (Analytics)
    • 💬Conversations
      • Review Past Conversations
      • Conversation Links
      • Training Better Responses
      • Live Chat
        • Human Handoff Automation (for Live Chat)
    • 📚Knowledge Base Explained
      • 💽Data Storage (Characters)
        • Storage (Characters) Example
      • Copy & Paste Text
      • Upload Documents
      • Scrape Websites
        • 24-hour Auto-Scraping
        • Scraping a Google Doc
        • Google Docs
      • Question & Answer Pairs
      • Data & Content Security
      • Citations/ Sources
      • HTML Rendering (Embed Images & Videos)
    • ✍️Prompting
      • What is a Base System Prompt?
      • Writing a Base System Prompt
      • Prompt Examples (Marketplace)
        • Base System Prompt Template (General)
    • 🔧AI Agent Settings
    • 🎨AI Chat Widget
      • Customize Chat Widget Apperance
      • Chat Widget Pop-Up
      • Initial Messages Pop-Up
      • Chat Widget Voice
    • ⚙️Advanced Settings for AI Agent
      • Model Version
      • Prioritize Question/Answer Results
      • Chatbot Visibility
      • Temperature
      • Message Template
      • Support Email
      • Domains
      • Show Data Sources in Chat Widget
      • Debug Mode
    • Leads 2.0
    • 📈Leads (Legacy)
      • Overview of Lead Generation
      • Lead Collection Form Fields
      • Lead Collection Webhook URL
      • Lead Collection Email Notification
      • In Chat Lead Collection Base System Prompt
      • Sending Lead Data to Zapier
      • Sending Lead Data to GHL
      • Sending Lead Data to Zoho CRM
    • 📅Scheduling
      • AI Scheduling - Simplified
      • AI Scheduling - Experimental (Beta)
        • What is Scheduling?
        • Calendar Integration
          • Google Calendar
        • Appointment Scheduling Activation
        • Appointment Scheduling Webhook URL
        • Appointment Scheduling Email Notification
        • Appointment Scheduling Base System Prompt
        • The Appointment Scheduling Functions & Customizing the Appointment Scheduling Prompt
    • 🧊Integrations
      • Embed Chatbot on a Website
      • Zapier App
      • GoHighLevel (GHL)
      • Instagram DM
      • Facebook Messenger
      • WhatsApp
      • ElevenLabs Voice
      • Discord
    • 🤖Troubleshooting
      • How to Respond in Any Language
      • Responses are Too Long
      • Debug Mode
      • Clickable Links in Responses
    • 🌌Functions (Labs)
      • Custom Functions
        • How Custom Functions Work
        • Code Generation Prompt for Custom Functions
        • Stock Market Data - Custom Function
        • Shopify - Custom Function
        • Airtable - Custom Function
        • Google Sheets - Custom Function
    • 🔄Vault
      • OpenAI API Key (ChatGPT)
      • Anthropic API Key (Claude)
      • xAI API Key (Grok)
      • Eleven Labs API Key
  • 👑MasterChat
  • White Label
    • 🤑What is White Labeling?
    • 👤Client Sub-Accounts
      • Create Sub-Account
      • Sub-Account Wallet
      • Sub-Account Storage Balance
      • Sub-Account Extra AI Agents
      • How to clone a chatbot to a sub-account
    • 🔗Custom Domain
      • Troubleshooting Custom Domain Deployment DNS Issues
    • 🏗️The SaaS Configurator
      • Create Subscription Package
        • Custom Packages + Settings
      • Add-Ons
        • Storage (Characters) - Add Ons
        • AI Agent Rebilling - Add Ons
        • MasterChat - Add Ons
        • Advanced Scraper - Add Ons
    • 👍White Label API
      • API Documentation
      • AI Agent API
        • Message AI Agent
        • Create AI Agent
        • Retrieve AI Agent
        • Update AI Agent
        • Delete AI Agent
      • Knowledge Base API
        • Add AI Agent Q/A
        • Add URLs to Scrape
        • Add Files (Pdf, Doc etc.)
      • Conversations
        • AI Agent Conversations
        • Retrieve Conversation
        • Delete A Conversation
      • Sub-Accounts
        • Create Sub-Account
        • Retrieve Sub-Account
        • Update Sub-Account
        • Delete Sub-Account
      • User
        • Retrieve User's Data
      • Examples
        • Create New Sub-Account (Zapier Example)
        • White Label API x Zapier X Slack Example
        • AI Chatbot Chrome Extension
    • 👾White Label (Your) Marketplace
    • 😇White Label Free Trials
      • Free Trial Settings (No CC Req.)
      • Free Trial Settings (CC Req.)
    • 🎨Custom Dashboard Styling
  • Agency Settings
    • ⛳Agency Dashboard
    • 👥User Permissions
    • 😎Agency Profile
    • 👥User Access
    • 💳Connect Stripe
    • 🔗Custom Menu Links
    • 🤘Default Prompts
  • Account Management
    • ⚙️Billing Usage & Settings
    • 💲Agency Billing
      • Subscription Plans
      • Change Subscription Plan
      • Update Credit Card
      • Download Invoice
      • Refunds
      • Cancel Subscription
    • 💱Agency Wallet
      • The Agency Wallet System
      • Agency vs Sub-Account Wallet
      • Auto Billing
      • Add Funds to Wallet
      • AI Messages Costs
      • AI Agents Costs
      • Storage (Characters) Costs
    • 🤲Admin Account Profile
      • Change Password
      • Google Auth Login
  • Support
    • 🤝Need Help?
    • 🔓Security & Compliance
      • Data Privacy & Security Report
      • GDPR
      • Terms & Conditions
      • Privacy Policy
      • Data Processing Agreement
      • AI Model Data Usage
      • Service Level Agreement
    • ⚡Discord Community
    • 📹Weekly Office Hours
    • 🙌FAQ
      • General
      • Localization
      • Data/Security
      • Set Up
      • Password
      • Technical Questions
      • Sales/Onboarding
      • Marketing/Pricing
      • Where can I find...?
      • Other
      • Alternatives to Stripe Connect
    • 📰Changelog/ Roadmap
    • 🍭Resources
      • Sales Deck
      • 💰AI Agency 101
        • How to Price Your AI Chatbots
        • How to Get More Clients
        • The Value Proposition of AI Agents
        • AI SaaS Funnel Explained
    • 🤑Affiliate Program
Powered by GitBook
On this page
  • What is a prompt?
  • 1. Define Business Context
  • 2. Add Basic Business Knowledge
  • 3. Tone and Language
  • 4. Rules of Engagement
  • 5. Example Conversation
  • 6. Output Formatting
  • 7. Step by Step Thinking
  1. AI Features
  2. Prompting

Writing a Base System Prompt

Review the different elements of how to write a base system prompt.

PreviousWhat is a Base System Prompt?NextPrompt Examples (Marketplace)

Last updated 1 year ago

What is a prompt?

Writing a prompt for an AI assistant or agent is like giving directions to a friend who's ready to help you with a task but needs clear instructions on what you want.

Here's a simple guide to help anyone understand how to write an effective prompt:

1. Define Business Context

Start by outlining the specific business the AI assistant will represent. Include key details such as the industry, product or service offerings, target customer base, and any unique selling points. This sets the stage for the AI to understand the environment it will operate within.

Your task is to provide customer support for [Business Name], a [Industry Type] company specializing in [Product/Service Offerings]. Our customers range from [Target Customer Base] who value [Unique Selling Points].

2. Add Basic Business Knowledge

Ensure the prompt includes instructions for the AI to access and utilize a wide range of information related to the business. This can include product manuals, FAQs, company policies, customer service scripts, and any other relevant data.

You have access to all our product manuals, FAQs, company policies, and customer service scripts. Use this information to answer queries accurately and provide solutions to our customers.

3. Tone and Language

The tone of communication is crucial in customer support. Specify the desired tone (e.g., friendly, professional, empathetic) and any language preferences or requirements. This helps the AI align its responses with the company's brand voice.

Communicate in a [Specify Tone] tone, maintaining a professional yet empathetic  approach. Use [Specify Language or Jargon] where appropriate, but ensure explanations  are clear and accessible to all customers.

4. Rules of Engagement

Outline specific guidelines for how the AI should interact with customers. This includes how to handle sensitive customer information, privacy considerations, escalation protocols for unresolved issues, and any limitations on the AI's role in customer support.

Always prioritize customer privacy and data protection. For unresolved issues, follow our  protocol by providing the customer with [Escalation Steps]. Do not attempt to resolve issues beyond your scope; instead, direct customers to [Next Steps].

5. Example Conversation

Offer examples of common customer queries and ideal responses. This helps the AI understand the types of questions it will encounter and the level of detail expected in its answers.

Example Queries:
- Query: 'How do I reset my product?'
- Ideal Response: 'To reset your product, please follow these steps: [...]'

- Query: 'What is your return policy?'
- Ideal Response: 'Our return policy allows for returns within 30 days of purchase, 
provided the product is in its original condition. For the full policy, visit [Link].'

6. Output Formatting

Specify how you want the AI to format its responses to customers. This ensures consistency and readability, making it easier for customers to follow instructions or understand the information provided.

Format your responses to customer inquiries using clear, concise language. When providing instructions or solutions, use bullet points or numbered steps for ease of understanding.

7. Step by Step Thinking

Guide the AI to approach problem-solving and query resolution in a logical, step-by-step manner. This not only aids in generating coherent and structured responses but also mirrors the thought process a human agent might use, enhancing the customer's experience.

When addressing customer queries, follow a logical problem-solving approach:
1. **Identify the Customer's Need:** Clarify the customer's issue or question to ensure you understand what they are asking.
2. **Gather Relevant Information:** Use the provided resources (FAQs, product manuals, policies) to find the information relevant to the customer's query.
3. **Formulate a Response:** Based on the information gathered, craft a response that directly addresses the customer's need. If the query involves troubleshooting, provide step-by-step instructions.
4. **Check for Completeness:** Before sending the response, ensure it fully addresses the query and is formatted for clarity.
5. **Offer Further Assistance:** End your response by asking if the customer needs more help, directing them to additional resources or escalation paths if necessary.

✍️
Base System Prompt Template (General)