Chatlayer Documentation
Get in touchAbout Chatlayer
  • Welcome
  • What's new
  • Send feedback
  • start quickly
    • Leadzy tutorial
      • 0. Introduction
      • 1. New bot, new block
      • 2. Understand your users
      • 3. Collect and display user input
      • 4. Steer the conversation with Conditions
      • 5. Empower your bot with Actions
      • 6. Set up a channel and publish your bot
    • Templates
      • Banking
      • E-Commerce Returns
      • E-Bike Shop
      • E-Scooter Support
      • Feedback
      • Find Nearest Location
      • GPT
      • 🆕Gym
      • Job applications
      • Knowledge base AI template
      • Lead generation
      • 🆕NPS
      • Restaurant
      • Retail
  • navigation
    • Analytics
      • Dashboard
      • Customers
      • Conversations
      • User flow
      • Intents
      • 🆕Funnels [Beta]
    • Bot builder
      • Flows
        • Canvas functionalities
        • Collaborate with team members
        • Manage your flows
        • 🆕[Beta] Export and import flows
      • Bot dialogs view
      • Translations
      • Events
    • NLP
      • Dashboard
      • Intents
      • Expressions
      • Entities
      • Train
      • NLP settings
      • Improve
    • Knowledge base AI
      • Add content to your KBAI
      • Build your KBAI flow
      • Use your KBAI source URL in a button
      • Use tags to limit your KBAI content
      • 🆕Use Tables to store your KBAI questions
      • 🆕Manage handover where KBAI is unsatisfactory
    • History
      • Conversations
      • Execution logs
      • Versions
    • Channels
    • Tables
      • Create a table with records
      • Column types
      • Operate on your records
        • Insert record
        • Update record
        • Retrieve record
        • Delete record
      • API
    • Settings
      • Bot settings
      • Offloading
      • Variables
      • Voice
      • Import/Export
  • build your bot
    • Conversation design
      • Plan your bot
      • Conversation design workflow
    • Flow logic
      • Blocks
        • Message
        • Condition
        • Collect input
        • Action
      • Go-to connections
    • 🆕Emulator
    • Tips & best practices
      • Route your flow depending on the time
      • Improve the Not understood block
        • How to create better not understood messages
        • Not understood counter
        • Not understood Google search
      • Go to previous block
      • Recognizing a returning user
      • Skip introduction message
      • Route your flow depending on the channel
      • Reuse flows
      • Connect two bots to each other
  • understand users
    • Natural language processing (NLP)
      • Basic NLP concepts
      • Detect information with entities
        • Match entities
        • Contextual entities
        • System entities
        • Composite entities
      • NLP best practices
        • Word order and diversity of expressions
      • AI intent booster
      • Train your NLP
      • Context
      • NLP import & export
      • Sentiment analysis
    • Languages
      • Supported languages
      • Make your bot multilingual
      • Change language within the conversation
  • set up channels
    • Add a channel to your bot
    • All channels
      • 🚨Facebook Messenger [Deprecated soon]
        • Facebook Admin Removal
        • Facebook Webview Whitelisting
        • Facebook Messenger API updates for Europe
      • 🚨Google Assistant [Deprecated soon]
      • Webhook
      • Web
        • 🚨Web V1 [Deprecated]
          • Customize web widget
          • Live example web widget
        • 🆕Web V2
          • 🆕From Web V1 to V2
          • 🆕Web V2 methods and options
    • Sinch Conversation API
      • Configure your Sinch Conversation API
      • 🆕 Make the most of RCS with Carousels
      • WhatsApp Business API
  • integrate & code
    • API calls
      • Configure your API integration
      • Advanced API features
      • V1 API Reference
      • Custom integrations 101
    • Code editor
      • [Example] Sending data to Airtable (POST)
      • [Example] Retrieving data from Airtable (GET)
      • [Example] Making SOAP requests
    • App integrations
      • Airtable
      • Freshdesk
      • Freshdesk Messaging
      • 🆕Gmail
      • Intercom
      • Mailgun
      • OpenAI: GPT-3, ChatGPT and GPT-4
      • Salesforce
      • 🆕Slack
      • Topdesk
      • Zendesk Support
      • Zendesk Sunshine (beta)
    • 🆕Expression syntax
    • Human handover & live chat
      • Sinch Contact Pro
      • #Interact
      • Genesys Cloud
      • Offloading Webhook
      • Salesforce Service Cloud
      • Sparkcentral by Hootsuite
      • Zendesk Chat
    • Chatlayer messages specifications
  • Publish
    • Publish your bot
      • Publish a flow
  • Analyze & maintain
    • Analytics definitions
    • Data retention
    • Maintenance
    • Session
    • Track events for analytics
  • VOICE
    • 🆕Send bot response as audio
    • Voicebots
      • Create a voicebot
      • Voicebot-specific actions
      • Test your voicebot
      • From chat to voice
  • access & support
    • Identity & Access
      • Single Sign-On (SAML SSO)
    • Billing & subscription
    • Get in touch
    • Chatlayer glossary
    • SaaS Regions & IP Ranges
    • Status
    • Debug your bot
      • No correct response
      • Collect input not working
      • Video isn't working
Powered by GitBook
On this page
  • 1. Provide built-in answers for crucial matters
  • 2. Use your KBAI for other questions
  • 3. Count the number of unsatisfactory answers
  • 4. Transfer to agent after multiple unsatisfactory answers

Was this helpful?

  1. navigation
  2. Knowledge base AI

Manage handover where KBAI is unsatisfactory

When your Knowledge base AI finds a responses that is unsatisfactory, doesn't find a response, or fails to find one, recognizing when to hand over to human support is key.

PreviousUse Tables to store your KBAI questionsNextHistory

Last updated 10 months ago

Was this helpful?

If your cannot retrieve an appropriate answer to the user's question, it will result in "no finding." This behavior ensures that KBAI avoids providing unrelated answers or hallucinations.

To maintain a balance between efficiency and support, it's best practice to allow users to reformulate their questions and provide an option to connect with a human agent when the bot cannot assist effectively.

This article presents a flow model that detects intents before using . The model will count the number of times where an answer was unsatisfactory before handing the user over to an agent.

The handover flow presented in this article follows this flowchart:

Let's see step by step how this flow is working.

1. Provide built-in answers for crucial matters

2. Use your KBAI for other questions

For any question that is not urgent or that doesn't need a built-in answer, use the KBAI. Your bot will then see if an answer can be found based on your documentation.

3. Count the number of unsatisfactory answers

4. Transfer to agent after multiple unsatisfactory answers


This is what this handover flow looks like after it was build on Chatlayer:

When building your bot, there are typically some issues that would 100% of the times need the help of a human. To make sure these matters are tackled as early as possible, the best strategy is to catch them at the start of your flow by using .

Build your NLP model from your tab.

To use inside your bot, you'll need to or start with our .

Count the number of times that your bot wasn't able to help the user by incrementing a count with 1 each time you go through an unsatisfactory answer.

On Chatlayer, you can increment variables inside the section inside a block.

Please note that for this tutorial we are using the new . If you're using the old expression syntax, you'll need to use the {counter|increment} syntax.

After 2 unsatisfactory answers, the user is .

🆕
intents
NLP
Knowledge base AI
set up a KBAI flow
KBAI bot template
variable
Go to
expression syntax
handed over to an agent
Knowledge base AI (KBAI)
Knowledge base AI (KBAI)
Example of handover where the KBAI fails.
KBAI handover flow model.
Provide built-in answers by building a strong NLP model.
Use KBAI to find an answer when the bot doesn't understand what the user said.
Example: we pass on an incremented {count} variable to the next block.
After 2 unsatisfactory answers, hand over the bot to an agent.
KBAI handover flow model build on Chatlayer.