LogoLogo
  • GETTING STARTED
    • Welcome to the NLX platform
    • How NLX works
    • Guides
      • Analytics dashboard
      • Chat
      • Generative Journey (Slots)
      • Model Context Protocol
      • Voice
      • Voice+ script
      • Touchpoint components
        • Carousel modality
        • Video modality
    • Terms & concepts
    • Generative AI
    • Developer
  • Build
    • Workspace setup
    • Flows
      • Intro to flows & variables
      • The Canvas
      • Flow settings
      • Nodes
      • Flow appearance
    • Resources
      • Actions
        • Implementation
        • Request model
      • Analytics tags
      • Context variables
      • Data requests
        • Implementation
        • Response model
        • Request model
      • Knowledge bases
        • Ingest content
        • Add metadata (beta)
        • Apply KB
      • Lifecycle hooks
        • Implementation
      • Modalities
      • Secrets
      • Slots (custom)
        • Adding values
        • Translating slots
      • Voice+ scripts
        • Add + download script
        • Deploy script + install SDK
        • Create Voice+ flow
    • Integrations
      • Channels
        • Alexa
        • Amazon Chime SDK
        • Amazon Connect
        • AWS End User Messaging SMS
        • AWS End User Messaging Social
        • Bandwidth
        • Genesys
        • Twilio
        • Zendesk Sunshine
      • LLM services
        • Amazon Bedrock
        • Anthropic
        • Azure OpenAI
        • Cerebras
        • Cohere
        • Google Vertex AI
        • Groq
        • NVIDIA
        • OpenAI
        • xAI
      • NLP
        • Amazon Lex
        • Google Dialogflow
        • Google Dialogflow CX
        • Custom NLP
    • Translations
  • Deploy & test
    • Applications
      • Attach flows
      • Assign default behavior
      • Add channels
        • API
          • REST API
        • Alexa
        • Amazon Chime SDK
        • Amazon Connect
        • AWS End User Messaging SMS
        • AWS End User Messaging Social
        • Genesys
        • Genesys SMS
        • Messenger
        • Microsoft Teams
        • Slack
        • SMS via Bandwidth
        • Twilio SMS
        • Twilio Voice
        • WhatsApp via Twilio
        • Zendesk Sunshine
      • Deploy
      • Optional: Set lifecycle
      • Optional: Set languages
    • Test
      • Test a conversation
      • Automated tests
      • Test an external integration
  • Analyze
    • Conversations
    • Analytics
      • Creating dashboards
      • Formulas & multi-metrics
      • Canvas analytics
    • Training
  • Workspace Settings
    • Escalation channels
    • Resource tags
    • Audit
  • Admin
    • Access control
      • Roles & permissions
    • Notifications
    • FAQ
    • Contact support
Powered by GitBook
On this page
  • What's Conversations?
  • Conversation history filters
  • View conversations
  • Add a conversation history tab
  • Delete a conversation history tab
  1. Analyze

Conversations

Review past conversation history between users and applications in your NLX workspace

Last updated 18 days ago

What's Conversations?

Conversations under the Analyze section of your workspace provides historical information on conversation sessions that have taken place with your deployed applications.

Viewing conversation history allows you to troubleshoot unique or common issues, pinpoint where one or more flows could be more efficient, where users might be losing interest, or where additional automations are needed.

To access, click Conversations in your workspace menu:


Conversation history filters

The following are all available conversation history filters you can use to narrow results:

  • Application: Filter by available applications in your workspace

  • Flow: Filter by available flows in your workspace

  • Region: Filter by Global region or European Union

  • Language: Filter by all available languages; workspace languages that have been selected for resources are ordered first in the list

  • Start/End time: Enter calendar date and time to filter conversation results within this window

  • User/Conversation ID: Filter by a specific user ID or conversation ID

  • Search: Filter by user utterances logged in the Flow message column. Results will include all conversations containing your search keyword(s)

  • Channel: Filter by all possible communication channels

  • User engagement

    • Engaged only: Filter by conversations that recorded at least one response from the user

    • Unengaged only: Filter by conversations that did not record any responses from the user

  • Tags: Filter by any tags in the workspace; you may select more than one to filter by

Click Save when done to preserve your tab and any dropdown selections. You can make adjustments to dropdown selections and select the Reload link to view new filtered results.


View conversations

To view the results of conversation histories, select Conversations in your workspace menu.

You may apply filters to the Main default tab or create new tabs and define a preset of filters. You may also adjust any filters to existing tabs to automatically refine results (does not save the filter for future visits unless in edit mode with the tab).

Each row of the results table represents a unique conversation session:

  • Date: Day and time a conversation session started

  • Application: The conversational AI application the user engaged with

  • Channel: The communication channel used for the conversation

  • Duration: Length of the conversation session

  • Flow message: The initial user utterance submitted in a conversation (N/A indicates unengaged user)

  • NLP score: Confidence level of the NLP in routing users to a flow

  • Average response time: Length of time for the conversational AI to reply to the user

  • Flow: All flows invoked during the conversation

To view more details from a specific conversation, select any row from the results table:

The Conversation details pop-out menu provides advanced info, including Conversation ID, User ID, and a full transcript of messages between your conversational AI and a user.

Add a conversation history tab

To add a tab with predefined filters to your workspace's conversation history dashboard:

  • Navigate to Conversations in workspace menu > click + Add tab

  • Enter a name for the tab (might reference a channel, specific application, or region, for example)

  • Click Save

For additional edits to existing tabs, select the tab name and click the edit icon that appears.

Adjust filters to existing tabs to automatically refine results; however, this does not save the applied filter(s) for future visits unless saving them while in edit mode with the tab.

Delete a conversation history tab

To add a tab with predefined filters to your workspace's conversation history dashboard:

  • Navigate to Conversations in workspace menu > Click on tab name

  • Select the Edit tab option

  • Click Delete tab

  • Select Confirm delete

Tags: Displays nodes that have been visited by the user with

Copy icons for conversation and user IDs are also provided, making it easy to copy and paste these values into the Conversations filter fields or when viewing .

Select from to create a preset of parameters for conversations you wish to view

Canvas analytics
one or more filter dropdowns
Analytics tags applied
Conversation details from a selected conversation