LogoLogo
  • Introduction to the Ebbot Platform
  • Ebbot Platform
  • Bot basics
    • Scenarios
    • Entities
    • Triggers
    • Training center
  • Scenarios
    • Cards and syntax
      • File Input
      • Text card
      • Input
      • Buttons
      • Image
      • File
      • Carousel
      • Location
      • List
      • Contact Agent
      • Rating request
      • Custom component
      • CoBrowsing
    • Transition
    • Card properties
  • AI Insights
    • Setup and Configuration
    • Using the Insights Dashboard
  • EbbotGPT
    • Knowledge
      • Data source transformer
      • Source types
        • File
        • Website scrape
        • Docx file
        • TOPdesk API
        • Sitevision API
        • SharePoint API
          • Create app with Sites.FullControl.All permission in Azure
          • Ebbot SharePoint Postman Guide
        • Confluence API
    • Configurations
    • Persona
    • GPT Evaluation
    • Embedder models
    • EGPT models
  • Custom vocabulary
  • Tutorials
    • Create your first scenario
      • Select a trigger
      • Add bot responses
  • Data Object
  • Release notes
  • For developers
    • Ebbot SDK
    • Safe Exchange API / Vault
    • Subdomain manager
  • EbbotGPT API
  • Chatbot & Live chat
    • Install chat widget
    • Chats API
    • Chat widget API
    • Datasource API
    • Sales tracking for live chat
    • Webhook
      • Incoming webhooks
      • Outgoing webhooks
    • SMS API
      • Authentication
      • Send SMS
      • Errors
      • Encoding
    • Python components
    • Intent detection (NLP)
  • Product guides
    • Product data feeds
    • Install guide
    • Product guide events
      • Product guide user events
      • Received events
      • Send events
    • API & webhooks
    • GA4 integration
    • Klaviyo integration
  • Messenger marketing
    • Install popup
    • API & webhooks
  • For chat agents
    • Ebbot Chat
      • Settings modal
      • Queue
      • Topbar Stats
      • Menu
        • Power-Ups!
        • Quick Replies
  • INTEGRATIONS
    • Ebbot Live Chat in Zendesk
      • Setup guide
    • Active Directory - SAML
    • Configure SAML in Azure
Powered by GitBook
On this page
  • Dashboard Overview & metric breakdown
  • 1. Total Chats
  • 2. Resolution Rate
  • 3. Sentiment
  • 4. Most Common Topics
  • Chat History Table
  • Viewing Chat Details and Insight Reasoning
  • Making the Most of Your Insights

Was this helpful?

  1. AI Insights

Using the Insights Dashboard

Once you have completed the setup and Insights are active, the AI Insights dashboard gives you a comprehensive view of your chat data. Here’s how to navigate and make the most out of your insights:


Dashboard Overview & metric breakdown

1. Total Chats

Displays the total number of chats analyzed in the selected period, with a comparison to the previous period to help you track trends in your chat volume.

2. Resolution Rate

How it’s calculated: Each conversation is classified based on whether a clear outcome was reached in the chat. If the issue is explicitly resolved, it’s marked as “Solved.” Otherwise, it’s “Incomplete,” “Unsolved,” or “Unsolved / No Info” if unclear.

  • Solved: The chat ended with a clear resolution.

  • Incomplete: The conversation did not reach a clear outcome, such as the user stopped responding.

  • Unsolved: The system could not solve the inquiry in a satisfying manner.

  • Unsolved/No Info: The bot expresses specifically that is lacks information to resolve the user's inquiry. This could be interpreted as a knowledge gap.

Resolution Over Time: Shows how resolution types have changed across recent months. This helps you monitor improvements or spot periods needing attention.

3. Sentiment

Displays the distribution of Positive, Negative, and Neutral conversations, helping you gauge overall customer satisfaction and changes in sentiment over time.

How it’s calculated: Only user messages are analyzed. Positive sentiment is flagged if the user expresses gratitude or satisfaction, especially at the end of the chat. Clear complaints or frustration are classified as negative. All other cases, or a mix, are considered neutral. (Bot messages are always ignored.)

4. Most Common Topics

How it’s calculated: AI Insights reviews each conversation and assigns up to two relevant topics that reflect the user's main issues. The first button the user clicks is prioritized, and explicit statements from the user determine which topics are set on the conversation. If no clear issue is mentioned, no topic will be set. Available topics are customized for each customer’s needs on the Config page.


Chat History Table

Below the main charts, you’ll find a detailed table of individual chat records, showing:

  • Username: The participant in the conversation.

  • Resolution: The outcome status (e.g., Solved, Incomplete, Unsolved, Unsolved / No Info).

  • Sentiment: The tone of the conversation (Positive, Neutral, Negative).

  • Topics: The main topics identified in the chat.

Viewing Chat Details and Insight Reasoning

Clicking on any chat entry in the chat history table will open a detailed modal, allowing you to:

  • View the full conversation transcript: Read the entire chat to understand the context.

  • See detailed insight breakdowns: For each identified topic, sentiment, or resolution, you can see the AI’s reasoning, including the relevant parts of the conversation used for analysis.

  • Refresh insights: If needed, you can refresh the insights to reanalyze the conversation with updated settings or data. If a chat has no Insights yet, you can use this button to manually trigger the chat for analysis.


Making the Most of Your Insights

  • Track Trends: Use the dashboard to notice shifts in chat volume, resolution rates, or sentiment, which could signal changes in customer needs or agent performance.

  • Identify Focus Areas: Look for frequent unresolved issues, negative sentiment, or trending topics to prioritize improvements.

  • Investigate Details: Drill down into individual chat records for a deeper understanding of customer interactions and context behind the metrics.

PreviousSetup and ConfigurationNextEbbotGPT

Last updated 1 month ago

Was this helpful?