Activechat Manual
  • What is Activechat?
  • New? Start here
    • The basics
    • Set up your first project
    • Install the chat widget
    • Upload the knowledge
    • Explore the CRM
    • AI-assisted live chat
      • How to set context for AI hints
    • Live chat mobile app
    • Build your first automation
  • Conversational AI
    • For Customer Service Teams
    • For Product Managers
    • For Innovation Teams
    • For Marketers
    • For e-commerce
    • For developers
  • Help Guides
    • Setting up your team
    • Managing conversations
      • Customer attributes
      • User tags and segments
      • Searching for specific users
      • Agent tags (live chat groups and queues)
      • Triggering live chat sessions from the bot
      • Notifications with the TRIGGER block
    • Managing knowledge
      • Uploading business data
      • Question answering and live chat hints
      • Fine-tuning the large language model
    • Natural language automation
    • Building automations visually
      • Customizing your welcome message
      • Adding new skills
      • Navigating skills
      • Copying skills and blocks
      • Handling errors
    • Improving your virtual agent
    • Using live chat AI hints
    • Customizing automatic website page messages
    • Tracking website actions
    • Facebook Ads automation
      • How to set up a Facebook ads bot
      • How to use buttons and quick replies in a Facebook ads chatbot
    • Lead generation
    • Zapier integrations
    • Customizing your project
      • How to customize the chat widget
      • How to customize the Facebook chat widget
      • How to change bot settings
    • Pricing guide
  • Fundamentals
    • Terminology
      • Intents and entities
      • Contexts
      • Skills and events
        • Built-in system skills
          • /start
          • /default
          • /_default_fallback
          • /_start_live_chat
          • /_page_visit
          • /_error
      • Conversation elements
        • Messages
        • Buttons
        • Quick replies
        • Galleries / carousels
    • Messaging channels
      • Website chat widget
        • Installation
        • Customization
        • Voice input
      • Chat widget landing page
      • Facebook Messenger
        • Connect your page
        • 24 hour rule
        • Message tags
        • Persistent menu
      • Telegram
      • Email
      • Twilio SMS automation
    • Intents and bot skills
    • Conversation insights
    • Grow tools
      • Landing pages
      • Messenger links and QR codes
    • Broadcasting
  • Visual builder reference
    • Sending messages
      • TEXT
      • LISTEN
      • IMAGE
      • MEDIA
      • GALLERY
      • FILE
      • EMAIL
      • SMS
      • LEAD
    • Triggering events
      • SEND
      • CATCH
      • TRIGGER
      • LIVE CHAT
    • Manipulating data
      • DATA
      • ADD TAG
      • REMOVE TAG
      • JSON
      • STATUS
      • VALIDATION
    • Conditional logic
      • SWITCH
    • Timers and delays
      • TIMER
      • WAITFOR
      • WAITUNTIL
    • E-commerce blocks
      • CATEGORY
      • PRODUCT
      • VARIATIONS
      • SIMILAR
      • UPSELLS
      • CROSSSELS
      • Shopping carts
        • ADD TO CART
        • UPDATE CART
        • SHOW CART
        • CLEAR CART
        • CREATE ORDER
    • Natural Language
      • NLP
    • System attributes
    • System events
  • Integrations
    • Google services
      • Connect your Google account
      • Google Sheets
        • Searching and updating Google Sheets data
        • Building galleries with Google Sheets data
      • Google Calendar
        • Searching for events
        • Creating and updating events
    • Shopify
    • WooCommerce
    • Dialogflow
      • Building an agent
      • Using entities
      • Slot filling
      • Context management
      • E-commerce NLP
Powered by GitBook
On this page

Was this helpful?

  1. Help Guides

Improving your virtual agent

PreviousHandling errorsNextUsing live chat AI hints

Last updated 3 years ago

Was this helpful?

The quality of your customer service automation will depend mostly on how good your virtual agent is at guessing the customer’s intent. It’s important to monitor the agent’s performance regularly to check which phrases your customers are using to express their intentions.

To help with that, we’ve built Insights – an AI-based tool to help you fill your with actual phrases that your customers are using.

You can extract insights from actual conversations that happen in your agent or import phrases from text files and other live chat platforms like Zendesk, Intercom, Freshdesk, or Livechat.

Go to the “Automation – Insights” menu and choose the source for your insights. If you select “Chat history”, choose the date range also – it will limit the analysis to specific dates. Depending on the volume of conversations that you have, this should be done on a weekly or daily basis. Please remember – the more training phrases you add to your Intents, the better your bot will be at guessing similar phrases used by customers to specify the same intent.

If you’re already using another live chat tool, you can import conversation transcripts as plain text files (one customer’s message per line). For Zendesk users, we support native Zendesk transcripts export format. Here are some text files from various domains to help you get started and experiment with this feature:

Once you choose the file (or the date range for chat history) and click “Get insights”, Activechat will process the data and group similar phrases into specific topics automatically. All that’s left to do then is choose some phrases (or even topics as a whole) and add these phrases to specific intents, repeating as necessary. This will make your agent smarter, and similar phrases will be triggering that intent from now on.

Once you choose some phrases and click the “Add selected to intent” button, select the intent where you want these phrases to be added to (or hit “New intent” to create one), choose the intent in the tree on the left, and click “Add to intent” again. This will launch the bot training process, and in a couple of moments, your bot will get smarter!

Repeat this process as needed, until most of the phrases your customers use are assigned to some intent and automated.

Adding new phrases from the Insights
Adding new phrases from Insights to the intent
These phrases are already added to the “Hello” intent
Coffee shop phrases ⬇️
Banking phrases ⬇️
IT support phrases ⬇️
Example FAQ phrases ⬇️
intents