Skip to main content

​
How to Train Periskope AI

1

Go to the AI Knowledge Base

To get started with training your Periskope AI, head over to AI > Knowledge Base
AI Knowledge Base interface
2

FAQs vs Documents

You have two ways to train the AI: by setting up FAQs or uploading a Training Document
FAQ and Documents training options
  1. FAQs: Better for handling specific questions and instructions to respond. (e.g. have AI ask follow up questions and debug an issue)
  2. Documents: Better for giving AI large contexts (e.g. for finding information about company services and answering a relevant question)

​
Structuring Your Knowledge Base

​
How to Structure FAQs

FAQs are essentially prompts for the AI Agent and should be structured as such. A question in the FAQ is used by the AI to search for an similar questions and the Answer tells the LLM what to do in response. Creating and tuning your FAQs to get the results that you want, may take multiple tries to acheive. If you have little experience with prompt engineering, or would like a deep dive and learn the best practices, you can read up on it here: Prompt Engineering Guide In general, when creating FAQs, follow these best practices for optimal AI responses:
  1. Include Multiple Question Patterns
    • Add various ways users might ask the same question
    • Example for a pricing question: 
      Q: How much does your service cost?
Q: What are your pricing plans?
Q: Can you tell me about your subscription fees?
A: Our service has three tiers:
- Basic: $10/month
- Pro: $25/month
- Enterprise: Custom pricing
    AI Knowledge Structuring 1

    Adding multiple questions to an FAQ for better identification

  2. Add Instructions for controlled AI Responses
The new FAQ structure includes a separate Instructions field where you can guide the AI’s response behavior without using special tags.
New FAQ Structure

New FAQ Structure with Separate Instructions Field

FAQ Structure Components:
  • Question: The customer question or query variations
  • Answer: The response the AI should provide to customers
  • Instructions: Special behavior instructions for the AI (separate field)
Types of Instructions:
  • Basic Instructions 
    Ask for the user's account email before providing specific account details
  • Conditional Instructions 
    If user mentions error code, ask for screenshot before troubleshooting
If user asks about pricing, confirm their region first
  • Follow-up Instructions
    Add follow-up instructions for multi-turn conversations if you wish the AI to follow up with different responses or escalate the issue by raising a ticket. Yes, the AI Agent can raise a ticket automatically to escalate an issue to a human! 😄 
    ONLY If they are facing issues with adding a new user, like they are unable to add any more users, it is likely their plan supports limited number of users. To add more, they'll need to upgrade. Find out if that is the case and if so you can ask them to upgrade from Settings > Manage Plans or notify the sales team to step in.

​
How to Structure Documents

When uploading training documents, organize information for better AI comprehension:
  1. Topic-Based Paragraphs
    • Group related information into single, focused paragraphs
    • Keep each paragraph focused on one main topic
    • Example: 
      [Product Features]
Our platform includes real-time analytics, custom reporting, and team collaboration tools. All features are accessible through our dashboard and come with detailed documentation. The analytics module provides instant insights into customer behavior and engagement metrics.

[Security Measures]
We implement industry-standard encryption for all data transmissions. Our servers are hosted in ISO-certified data centers with 24/7 monitoring. We conduct regular security audits and maintain SOC 2 compliance.
  2. Hierarchical Information
    • Start with general information
    • Follow with specific details
    • End with examples or use cases

​
Knowledge Base Optimization Tips

​
FAQ Best Practices

Question Variations
  • Include different ways customers might phrase the same question
  • Consider regional language differences and terminology
  • Add common misspellings or abbreviations
Answer Quality
  • Keep answers concise but comprehensive
  • Use bullet points for multiple items
  • Include relevant links or references
  • Test answers with real customer scenarios
Instruction Effectiveness
  • Be specific about when and how AI should behave
  • Use conditional logic for complex scenarios
  • Include escalation criteria for human handoff
  • Test instructions with edge cases

​
Document Organization

Content Structure
  • Use clear headings and subheadings
  • Group related information together
  • Include examples and use cases
  • Keep technical jargon to a minimum
Information Hierarchy
  • Start with overview information
  • Progress to detailed explanations
  • End with troubleshooting or advanced topics
  • Cross-reference related sections

​
Training Optimization

Regular Updates
  • Review and update content based on customer feedback
  • Add new FAQs for recurring questions
  • Remove outdated information
  • Monitor AI response quality and adjust accordingly
Performance Monitoring
  • Track which FAQs are most frequently used
  • Identify gaps in knowledge base coverage
  • Monitor customer satisfaction with AI responses
  • Adjust training based on conversation outcomes
Start with a small set of high-quality FAQs and gradually expand based on actual customer interactions. Quality is more important than quantity when training your AI Agent.

​
AI Agent Behavior Configuration

The Prompts section allows you to define how your AI Agent should behave, communicate, and handle different scenarios. Access this through AI > Prompts.
AI Agent Prompts Interface

AI Agent Prompts Configuration

​
🤖 AI Agent Roles and Behaviour

AI Agent Roles and Behaviour Define how the AI should behave, its tone, and specific roles it should take when responding to customers. This field acts as the core personality and approach definition for your AI Agent. Key Configuration Areas:
  • Communication Style: Set formal vs. casual tone, empathetic vs. direct responses
  • Role Definition: Define if the AI acts as a customer support agent, sales representative, technical support, etc.
  • Response Approach: Configure proactive vs. reactive behavior
  • Brand Voice: Ensure consistency with your company’s communication standards
Example Configuration: 
You are Periskope's AI assistant that deals with customer conversations and works 
closely with the internal team at Periskope. You will face questions from clients where they might ask about 
a certain feature, have certain doubts, face errors, or need demos and meetings. You are to answer to the questions 
promptly when you know the answer to them. Think of yourself as the team coordinator - you respond to customers 
when there are doubts, and when there are actionable items in a conversation, you delegate them to the appropriate 
team member. You do not have the ability to schedule calls. When you don't know the answer to these 
questions communicate with the internal human team members. You should use private notes and tickets to communicate 
with the internal team. Private notes are for normal to moderate issues and questions and tickets are for high priority
issues. Please don't format any links in markdown format, send them as plain text e.g. "https://google.com".

​
🏢 Company Overview

Provide comprehensive context about your business that helps the AI understand your company and respond appropriately. This field acts as the foundational knowledge that informs all AI responses. Key Information to Include:
  • Products/Services: Detailed description of what your company offers
  • Company Values: Core principles that should guide AI responses
  • Communication Tone: Preferred style (formal, casual, friendly, professional)
  • Key Integrations: Tools and platforms your company uses
  • Common Customer Scenarios: Typical questions, concerns, or use cases
  • Business Context: Industry, target audience, and unique value propositions
Why This Matters:
  • Improves AI response quality and relevance
  • Ensures brand-consistent communication
  • Helps AI understand context for better decision-making
  • Provides background for appropriate escalation decisions
Example Company Overview: 
We are a customer support platform that integrates with tools like HubSpot, Google Sheets, 
Freshdesk, Zoho, and more. Our sales team consists of @support@hashtag.dev and @sales@hashtag.dev 
who handle client issues and sales inquiries. We focus on providing quick, helpful responses while maintaining a friendly, professional tone.

In essence, **Periskope transforms WhatsApp into a full-fledged CRM and team collaboration tool**—ideal 
for businesses that rely heavily on WhatsApp for communication.
Text fields in the Control Panel are System Instruction for the AI Agent Model. You will achieve best results if you apply good prompt engineering practices. To learn more about prompt engineering, go here: Prompt Engineering Guide

​
👨🏻‍💼 Human Agent Roles

Human Agent Roles Define when and how human agents should take over from AI, and specify team member responsibilities. This helps the AI understand who to escalate different types of issues to. Key Configuration Elements:
  • Team Member Responsibilities: Specify which team members handle which types of queries
  • Escalation Criteria: Define when issues should be escalated to humans
  • Handoff Procedures: Configure how the AI should transfer conversations
  • Notification Rules: Set up alerts for human agents
Common Handoff Scenarios:
  • Complex technical issues requiring expert knowledge
  • Sensitive customer complaints or disputes
  • Sales inquiries requiring personalized pricing
  • Account-specific questions needing access verification
Example Configuration: 
Engineering Team:
@engineer@hashtag.dev is an engineer who owns features like bulk messaging, scheduled messaging, AI flagging and AI Agent

Sales Team: 
@sales@hashtag.dev handles client issues or questions regarding pricing, POC, deals, demos and anything sales related.

​
🏷️ Ticket Creation Rules

Ticket Creation Rules Define the criteria and conditions for when tickets should be automatically created by the AI. This helps ensure important issues are properly tracked and assigned to the right team members. Configuration Guidelines:
  • Creation Criteria: Specify when AI should create tickets vs. responding directly
  • Ticket Content: Define what information should be included in tickets
  • Priority Assignment: Set rules for ticket priority levels
  • Assignment Logic: Configure how tickets should be assigned to team members
Best Practices:
  • Create tickets for technical issues that need internal team attention
  • Avoid creating multiple tickets for the same conversation
  • Keep ticket titles crisp and descriptive
  • Include relevant context and customer information
Example Configuration: 
Tickets are a way to keep track of important issues faced by clients. 
Tickets are to be created when it is clear that there is an error that needs to be fixed by the internal team. 
Keep the ticket title crisp and concise. Don't create multiple tickets in the same conversation.

​
📝 Private Note Creation Rules

Private Note Creation Rules Define when the AI should create private notes for internal team communication rather than responding directly to customers. Private notes are essential for internal coordination and information sharing. Common Private Note Scenarios:
  • Internal observations about customer behavior or needs
  • Important context that should be saved for future reference
  • Flags for potential upselling or cross-selling opportunities
  • Notes about customer preferences or special requirements
  • Questions for internal team members
  • Status updates on ongoing issues
Configuration Best Practices:
  • Keep private notes concise and actionable
  • Use private notes for moderate-priority internal communication
  • Reserve tickets for high-priority issues requiring immediate attention
  • Include relevant customer context and conversation history
Example Configuration: 
Private notes are your primary way of communicating with the internal members.
You can ask certain questions, create Tickets for the respective team members for the issue at hand. 
Keep the private notes short and crisp.

​
Response Quality Factors

The AI Agent’s response quality depends on several key factors: Knowledge Base Quality
  • Well-structured FAQs with multiple question variations
  • Comprehensive documents covering your business domain
  • Regular updates based on new customer queries
Prompt Configuration
  • Clear, specific behavior instructions
  • Appropriate tone and communication style settings
  • Well-defined escalation criteria
Team Role Definitions
  • Accurate team member responsibilities
  • Clear escalation paths for different issue types
  • Updated contact information and availability
Activation Criteria Tuning
  • Balanced activation rules (not too broad or narrow)
  • Custom rules that reflect your business needs
  • Regular refinement based on performance monitoring

​
Advanced Configuration Tips

Monitor and Adjust
  • Regularly review AI Agent conversations to ensure quality responses
  • Adjust activation rules if the AI is responding too frequently or not enough
  • Fine-tune response delays based on your team’s availability
  • Update knowledge base content based on common customer queries
Best Practices
  • Start with conservative activation rules and gradually expand
  • Ensure internal contacts are properly marked to avoid AI interference
  • Regularly update team member roles and responsibilities
  • Test changes in the playground environment before full deployment
Troubleshooting Common Issues
  • AI not responding: Check activation criteria and ensure AI Agent is enabled
  • Too many responses: Tighten activation rules or increase response delay
  • Wrong team escalations: Update human agent roles and responsibilities
  • Poor response quality: Review and update knowledge base content
Start with default settings and monitor performance. Make incremental adjustments based on actual conversation outcomes rather than making large changes all at once.

​
Next Steps

After setting up your knowledge base: