LogoLogo
Click Here For More Support
  • 📍Get Started
    • Welcome
    • Who We Are
    • Our Product
  • 🤖AI Agent Engine
    • AI Agent Engine Basics
      • Get to Know Your AI Agent Engine
      • Glossary
      • Dashboard Overview
    • Manage Your Content
      • Response Types
        • Prewritten Plus Responses
          • Add New Prewritten Responses
          • Edit Prewritten Responses
          • Enrich Prewritten Responses
          • Response Refiner
        • Generated Responses
          • Web-Scraped Data
            • Troubleshooting
          • Documented Data
          • Enrich Generated Responses
        • Fallback Responses
      • Enrichments
        • Buttons
        • Quick Replies
        • Videos
        • Images & GIFs
          • Best Practices
      • Input Director
        • Copy & Paste Input Training
      • Best Practices
        • Locate Responses/Data
        • Revise Responses
        • Unpublish Responses
        • Content Formatting
        • Suppress Thumbs Up/Down
        • Content Groups
      • Upgrade to Context LLM
    • Install Your Chat
      • Web Installation
        • Advanced Pop-Up Options
      • InApp Webview Installation
        • App Provider Product Overview
        • iOS Advanced Install Guide
        • Android Advanced Install Guide
        • Passing Customer Identifiers
    • Enhance the Chat Experience
      • Pages
        • Add/View Chat Pages
        • Maintain State
        • Avatars
        • Chat Header Image
        • Input Container
        • Chat Background
      • Popups
        • Editor Field Definitions
        • Add/Edit Popups
        • Auto-Open
        • Prompt Bubble
        • Popup Button Image
        • Best Practices
      • Page Themes
        • Field Definitions
        • Adjust Page Themes
      • Activation & Drivers
        • Embed Webpages
        • Link Other Chats
        • Welcome Messages
      • Placement
        • Digital Placement
          • Chat Tile
          • Chat in Chat
        • In-Person Placement
      • Sponsor Inclusion
    • Features & Integrations
      • Channels
        • Facebook Messenger
          • Maintenance & Best Practices
        • Inbound SMS
      • Integrations
        • Ticket Commerce
          • Installation/Maintenance
          • Best Practices
        • Simpleview Integration
          • Listings
          • Events
          • Search Logic Summary
        • Zapier
          • Installation Guide
            • Connect to Salesforce
            • Connect to Google Sheets
        • FEVO
          • Installation Guide
          • Best Practices
        • Carbonhouse Integration
      • Features
        • Multi-Language Functionality
        • Mobile Ticketing Guide
        • Food & Beverage Finder
          • Installation/Maintenance
          • Best Practices
        • Weather Feature
        • Consent Form Feature
        • Satisfaction Score
        • 'Notify Subscription' Feature
    • User Management
      • User Types
      • Adjust User Type & Access
      • Add/Remove a User
      • Update Your Password
      • Unlock Your Account
      • Multi-Factor Authentication
    • Reporting & Analytics
      • Analytics Dashboard
        • Overview
        • AI Chat Performance Dashboard
        • Intent Explorer Dashboard
        • Intent Trends Dashboard
        • Intent Deep-Dive Dashboard
        • Bridge Agent Performance Dashboard
        • Mobile Ticketing Guide Dashboard
      • Data Reports
        • Conversation Transcripts
        • AI Resolutions Log
        • URL Link-Outs
        • Bridge Escalations
        • CSAT Entries
        • Ticket Commerce Records
        • End User Contacts
        • NLP Traffic Log
        • Input and Response Log
        • List URL Subscriptions
        • Get Response Feedback
        • Knowtifi Subscriptions
      • API Report Options
      • External IDs
      • UTM Tracking
      • Security Alerts
  • 📬Marketing Engine
    • Marketing Engine Basics
      • Get to Know Your Marketing Engine
      • Glossary
      • Login to Your Account
    • Marketing Calendar
      • How to Use the Marketing Calendar
    • Segments
      • Segments Overview
      • Uploading Contacts Manually
      • Uploading Contacts in Bulk
      • Importing a File into Unsubscribe List
      • Manage Contact Lists
      • Create Custom Object & Custom Fields for Contact Data Management
      • Contact Engagement Rules
      • Folders
      • Audience
        • Audience Dashboard
        • Audience Filters/Segments
        • Create a Meta Audience
        • Create a Audience Using Marketing Engine
      • Best Practices
        • Use Send Time Optimization
    • Templates & Landing Pages
      • Email Templates
        • Create & Preview an Email Template with Dynamic Content
      • SMS/MMS Template
      • WhatsApp Template
        • WhatsApp Carousel Template
        • WhatsApp LTO Template
        • WhatsApp Product Message Templates
      • Webpush Template
      • Mobilepush Template
      • Landing Page Template with a Form
      • Social Conversation Templates
    • Campaigns
      • Messaging Campaigns
        • Select Your SMS/MMS Sender Number
        • How to Create an SMS/MMS Campaign
        • Enable Double Opt-In
        • Messaging Campaign Report
        • Best Practices
        • SMS Regulations
          • SMS Regulations for India
          • SMS Regulations for Canada
          • SMS/MMS Regulations for USA
      • Social Campaigns
      • Email Campaigns
        • Create an Email Campaign
        • Update an Email Campaign
        • Email Campaign Report
        • Smart AI Tools
        • Best Practices
          • Reduce SPAM rate in emails
          • Craft Compelling Email Pre-Header Text
    • Journeys
      • Overview
      • Journey Blocks
      • Journey Templates
      • Create a Journey
      • Variant Testing
      • Conversion Tracking
      • Campaign or Journey Metadata
      • Advanced Filters for Sorting Campaigns/ Journeys
      • WhatsApp Journey
        • How to Use WhatsApp for Commerce
        • How to Send a WhatsApp One-Way Notification
        • Send a WhatsApp Audio Message
        • Automated WhatsApp Welcome Journey
        • WhatsApp Journey Report
      • Best Practices
        • Email Journey Strategy for Ticket Buyers
        • Journey Examples
    • Settings & Integrations
      • Integrations
        • Ticketing Integrations
          • Ticketmaster Integration
            • Best Practices
          • SeatGeek Integration
          • Glitnir Ticketing Integration
        • E-Commerce Integrations
          • Shopify
        • Website Tracking
          • Track Your Website
          • JavaScript Tracking Client
          • Track WordPress Websites
          • Track Shopify Stores
          • Enable User ID Tracking
        • Zapier Integration
      • User Management
        • Account Types
        • Add/Remove a User
        • Adjust Role & Access
        • Update Your Password
        • Two-Factor Authentication
      • Settings
        • Add Email Sender Addresses to Launch Campaigns
        • Connect Your Email Domain with the Marketing Engine
        • Connect Your Social Accounts
        • Connect your Shopify Store
        • Integrate Webpush Notifications
        • Setup Segment-based Engagement Rules
    • Factcubes
      • Fan Maturity Model
  • 💬Live Agent Engine
    • Get to Know Your Live Agent Engine
    • System Configuration
      • Installation Guide
      • Escalation Schedule
      • Multiple Team Involvement
      • Leave a Message & Contact Collection
      • Conversation Labels
      • Additional Channels & Placement
        • Bridge Placement
        • Bridge Email
          • Installation Guide
        • Facebook Messenger
    • Agent Overview
      • Logging In
      • Dashboard Overview
      • Profile Setup
      • Notification Preferences
      • Set Your Availability
      • Conversation Status
      • Assign a Conversation
      • Reply in a Conversation
      • Canned Responses
        • Add/Use a Canned Response
        • Modify/Delete a Canned Response
        • Best Practices
      • Participate in a Conversation
      • Private Notes & Mentions
      • Mute/Block a User
      • Prioritize Conversations
      • Resolve a Conversation
      • Export Transcripts
      • Macros/Automation
      • Keyboard Shortcuts
      • Ending Your Shift
      • Troubleshooting
    • Admin Overview
      • Adjust Team Assignments
      • Update Agent Status
      • Additional System Controls
    • Data & Reporting (Bridge)
    • Bridge Mobile App
  • SYSTEM UPDATES & SUPPORT
    • Help Center
    • Release Notes
      • Archived Product Updates
Powered by GitBook
On this page
  • Overview
  • Troubleshooting Scraped Data Scenarios

Was this helpful?

Last updated 8 months ago

Was this helpful?

Overview

Every time you add new imported data, we always recommend that you review results from our scraping tool within the response library. This is to ensure that:

  • The formatting of the content is readable by the LLM

  • The irrelevant page content isn't being scraped (ex. cookie policy, headers/footers, etc.)

  • Data is grouped and labeled correctly with a topic header

If you neglect any QA process of checking your data or testing it in your chat, you risk your chat providing users with wrong information.

Troubleshooting Scraped Data Scenarios

My chat is firing a prewritten response, but I want to use my web-imported data instead to generate a response.

Prewritten responses will ALWAYS fire before generating a response! To generate responses using your data, you will need to delete the existing prewritten response associated with that topic.

In this example, a user is wanting to know the price of valet parking:

Before: When Using a Prewritten Response

After: Deleted the Prewritten Response and Generated a Response

My web-imported data looks correct in my dashboard, but it is providing users with an incorrect answer.

There are a few things to review:

  • Ensure that you are not providing overlapping data in another response name.

    • For example: If you scraped a webpage where it stated that RV parking was $35, but you have outdated data in another response name stating that it's $25, it will confuse your chat and potentially fire an incorrect answer. Delete the outdated, overlapping information.

  • Make sure your data has appropriate topic headers to help direct your chat to generate responses.

    • For example: You scraped the following data from a school fundraising event page- "Any school that wishes to participate must email no later than August 30 with the school name and fundraising coordinator’s name/email address". Without a topic header, the system has no idea what this is for (school field trips, special events, etc.). Fix this by adding a topic header as shown below:

  • Edit scraped data and add additional context as needed within the Response Library.

    • For example: You scraped the following data from your parking and transportation page- "Small portable electric generators (600W or less) are permitted". Within your response library that data may look ok; however, without further clarification, the system doesn't know where generators are permitted. In this case, the system would assume because generators are permitted, they are permitted everywhere including inside the stadium. Edit this data in your response library to include more details like: "Small portable electric generators (600W or less) are permitted in parking lots. Generators will not be permitted inside the stadium."

The scraped data from my website is wrong. How can I determine which webpage it's from?

  1. Go to Studio -> NLP Manager -> Responses

  2. Search for the wrong data using keyword phrases in the Response Library as shown below:

  1. Once in the response, click the three dots in the top right-hand corner and then click Notes

  1. Within the notes section, you will see when the page was last scraped and the URL!

My website content was just updated. Is my previously scraped data updated as well?

No, you will need to scrape the page again to update your data in the response library.

Note: Manual edits can be made within web-scraped data responses in the dashboard. However, if a page is rescraped, those manual edits will be overwritten.

How do I determine if my data is useful or not?

Ensure the following when reviewing your data:

Unnecessary Data: You may scrape data like privacy overviews, dynamic content, or other information that is not needed to generate responses. We recommend deleting this data or deleting the entire response name.

Bad Chunking: Data like "Tickets are $15 for the show" may make sense to you, but not to your chat. Your chat wants to know as much context as possible like which show in particular is $15, when is it, when do tickets go on sale, is there kids pricing, etc.

Locate Responses/Data
Prewritten Response about Parking
Chunked Data with a Topic Header
Data That's Not Helpful When Building Responses
Generated Response with Enrichment
Example of Bad Chunking
Example of Good Chunking
Page cover image