Skip to main content
Back to Analytics Overview The Conversations History dashboard allows you to review transcripts of past conversations and label them for follow-up or further action. The Advanced Conversation Analytics feature provides a more detailed view including events and custom tags, which help you understand the interaction between the customer and the AI Agent. Custom tags can be reused across conversations for training purposes and to identify improvement areas.

​
View the Conversations History Dashboard

  1. Click Analytics on the left navigation pane. The Analytics panel displays the list of reports. Navigating to Conversations History Dashboard
  2. Click Conversations History under the Overview section of the Analytics panel. The Conversations History dashboard appears on the right side of the page.
  3. Select the appropriate filters and click Apply.

​
Filter Views Page

The Filter Views page is the landing page displayed when you open Conversations History. It lets you view, create, and manage conversation filters. From this page you can:
  • View available conversation filters and their configurations.
  • Create a custom filter to display only required data.
  • Access the Conversations History Dashboard for the selected preset.
Filters View Page

​
Prebuilt Filters

Prebuilt filters (also called presets) provide ready-made views for common use-case scenarios. They reduce the effort of manually reviewing each conversation to identify specific patterns. How it works:
  1. The system checks the configuration parameters and filter conditions for each conversation session.
  2. The conversation session is automatically mapped to the matching filter.
  3. Based on the selected date range, the system fetches and displays conversations that meet the preset’s criteria.

​
Types of Prebuilt Filters

Filter NameConfigurationDescription
All Conversations (default)Conversation Status: CLOSED; Containment Type: SELF-SERVICE; Is Developer: INCLUDE; Session Type: INTERACTIVEShows all conversations made during the specified dates regardless of other filter criteria. The “All Conversations” view cannot be edited.
Conversations with Multiple Intent Identification FailuresConversation Status: CLOSED; Containment Type: SELF-SERVICE; isDeveloper: EXCLUDE; Session Type: INTERACTIVE; Events: ≥ 2 intent identification failuresShows all conversations with unidentified intents in the selected date range.
Conversations with Multiple Entity RetriesConversation Status: CLOSED; Containment Type: SELF-SERVICE; isDeveloper: EXCLUDE; Session Type: INTERACTIVE; Events: ≥ 2 entity retriesShows all conversations with entity retries in the selected date range.
Conversations with Multiple Confirmation RetriesConversation Status: CLOSED; Containment Type: SELF-SERVICE; isDeveloper: EXCLUDE; Session Type: INTERACTIVE; Events: ≥ 2 confirmation retriesShows all conversations with confirmation retries in the selected date range.
Short Conversations resulting in User Drop-offConversation Status: CLOSED; Containment Type: USER DROP-OFF; isDeveloper: EXCLUDE; Session Type: INTERACTIVE; Events: ≥ 2 confirmation retries; Conversation Duration: < 30Shows conversations where users dropped off and conversations shorter than 30 seconds.

​
Feedback Prebuilt Filter

The Platform supports a Feedback filter on the Filter Views panel for creating custom feedback filters. The system groups and displays conversations based on:
  • Feedback Survey Template Type: NPS, CSAT, or Thumbs-up / Thumbs-down.
  • Operator: Equals to, Less than or equals to, Greater than equals to, Greater than, or Less than.
  • Value: The feedback survey score used for conditional logic evaluation.
Use the OR operator to group conversations with different survey types when multiple conditions need to be satisfied.

​
View Prebuilt Filters

  1. On the Conversations History page, prebuilt filters are listed under the Filter Views section. View Prebuilt Filters
  2. Click Read More next to a filter name to see its configuration details. View Prebuilt Filters
  3. Click any prebuilt filter name to open the Conversations History panel with the relevant data. View Prebuilt Filters

​
Create a Custom Conversation Filter

A custom conversation filter groups and displays selective conversation history data based on specific criteria.
  1. On the Conversations History page, click + Create Filter. Create Conversation Filter
  2. On the Create Conversation Filter panel, provide inputs for the following fields:
FieldOptionsDescription
View NameN/AName of the filter displayed on the dashboard.
DescriptionN/ADescription of the filter displayed on the dashboard.
Conversation StatusAll, Active, ClosedSelect All to view all conversations, Active for ongoing, or Closed for ended conversations.
Containment TypeSelf-service, User Drop-off, Agent TransferSelect Self-service for customer self-service conversations, User Drop-off for conversations where the user left, or Agent Transfer for conversations with agent transfer flow.
ChannelsAll Channels, Web/Mobile Client, Webhook, other configured channelsFilters conversations by the enabled channels.
LanguagesAll Languages, English (default), other configured languagesFilters conversations by the enabled languages.
Session TypeAll, Interactive, Non-interactiveFilters conversations by all channels, only interactive, or only non-interactive channels.
User IDInclude, ExcludeFilters conversations using platform user identities based on inclusion or exclusion.
Channel ID / Kore ID selectionToggleFilters using either Channel ID or Kore ID.
Task / IntentAll intents or specific intentsFilters conversations by all intents/tasks or specific ones identified during sessions.
Developer Interactions (IsDeveloper)Include, ExcludeFilters conversations by including or excluding developer interactions.
Time ZoneVarious global time zonesFilters conversations by the time zone of the session.
Conversation DurationConditional filters: Less than, Less than Equals to, Greater than, Greater than equals to, Equals to; Time units: Seconds, MinutesFilters conversations by session duration.
EventsConditional filters: Less than, Less than Equals to, Greater than, Greater than equals to, Equals to; Event names: Intent Identified, Intent not Identified, Success Task, Fail Task, Sentiment Event, User Sentiment Type, Entity Retry, Confirmation Retry, On Connect, End of Conversation, Debug Log, Welcome, Welcome Telegram, Welcome Facebook, Welcome Telephone, Standard Response Interruption, Message Node Interruption, Optional Entity, Script Node Failure, Service Node Failure, Agent TransferFilters conversations by event type and count.
FeedbackFeedback Type: NPS, CSAT, Thumbs-up/Down; Conditional filters: Less than, Less than Equals to, Greater than, Greater than equals to, Equals to; Score: NPS 0–10, CSAT 0–5, Thumbs-up/Down: 0 or 1Filters conversations by feedback type, condition, and score.
LabelsAll conversation labels or a specific labelFilters conversations by the selected label(s).
Custom TagsKey-value pairs combined with ANDFilters conversations using custom tags assigned by key-value pair.
  1. Click Save. Create Conversation Filter
The new custom filter appears on the Filter Views page and the Conversations History Dashboard reflects the specified criteria.

​
Edit a Conversation Filter

  1. Click the custom filter on the Filter Views page.
  2. Click the More Filters dropdown on the Conversations History panel. Edit a Conversation Filter
  3. Modify the required fields in the Edit Conversation Filter window.
  4. Click Apply. Edit a Conversation Filter

​
Filter Criteria

You can customize the Conversations History data view by selecting filter criteria on the dashboard.

​
Conversations History Dashboard

The Conversations History Dashboard displays the following information for each conversation session that meets the defined filter conditions for the selected date range.

​
Containment Type

The following containment types are displayed at the top of the individual Conversations History details panel:
  • Self-service: The conversation with the AI Agent was successfully completed by the user.
  • Agent Transfer: The conversation was transferred to a live agent using the Agent Transfer node in the Dialog Flow.
  • User Drop-off: The user stopped participating before the conversation was completed, due to an error in the flow or another reason. Containment Type

​
Labels

A custom label helps identify conversations that require follow-up or indicate an action item for an analyst during review. Custom Label Add a Custom Label
  1. Click the + Label button on the Conversations History panel for the required conversation session. Add a Custom Label
  2. In the Labels window, scroll down and click + Add.
  3. Enter the label name and click the confirm icon.
    You can select a different label color by clicking the color icon and using the color palette.
    Add a Custom Label
  4. Click Save.
Manage Custom Labels To edit a label:
  • Click + Label for the conversation session.
  • In the Labels window, click the edit icon for the label to modify.
  • Make changes and click the confirm icon.
  • Click Save.
To delete a label:
  • Click + Label for the conversation session.
  • In the Labels window, click the delete icon for the label to remove.
  • Click Save.

​
Other Conversation Parameters

The channel, language, date, and conversation duration are displayed at the top of the Conversation History analytics panel. Other Conversation Parameters

​
Conversation Summary

The following metrics are shown in the Conversation Summary:
  • User Messages: Number of messages sent by the user to the AI Agent.
  • AI Agent Messages: Number of messages sent by the AI Agent to the user.
  • Intents Identified: Number of user intents identified during the conversation.
  • Intent Unidentified: Number of utterances that did not result in intent identification.
  • Tasks Completed: Number of tasks successfully completed.
  • Failed Tasks: Number of tasks that failed.
Conversation Summary

​
Conversation Events

Conversation Events indicate the sequence of occurrences during a conversation triggered by customer inputs and AI Agent responses. Events are categorized as regular or error-based. Conversation Events Intent Found: Triggered when the AI Agent understands the user’s intent. The identified intent name is displayed.
EventDescription
Intent Not FoundTriggered when the AI Agent cannot understand the user’s intent.
Agent TransferTriggered when a live agent transfer is initiated.
Entity RetryTriggered when the user’s input is not identified and the AI Agent requests a retry.
Confirmation RetryTriggered when the AI Agent sends a confirmation request to the customer.
On ConnectTriggered every time a customer invokes Web/Mobile SDK (a conversation starts on the channel).
Sentiment EventTriggered when a customer’s sentiment is identified. The user sentiment type is displayed.
WelcomeTriggered when a message is received from the user and no channel-specific event is configured.
Welcome Event TelegramTriggered when a welcome event is received from Telegram.
Welcome Event FacebookTriggered when a welcome event is received from Facebook Messenger.
Welcome Event TelephoneTriggered when a telephone call is received from any voice channel.
EndTriggered when a conversation closes.
Debug LogTriggered when a debug log script runs for a script failure or service failure event.
Script FailureTriggered when a Script node failure occurs.
Service FailureTriggered when a Service node failure occurs.
RCS Opt InTriggered when Opt-In is received from the user for Rich Communication Services.
RCS Opt OutTriggered when Opt-Out is received from the user for Rich Communication Services.
User MessageTriggered when a customer sends a message to the AI Agent.

​
Enriched Chat Transcript

The Enriched Chat Transcript feature provides a detailed view of the conversation with all events associated with each message. It helps understand conversations at a granular level, identify issues, and improve AI Agent training. To view the Enriched Chat Transcript, enable the Show Events option (default) in the Chat History panel.
Disabling Show Events displays only the chat transcript without events.
Enriched Chat Transcript 1 Event labels that appear under Conversation Events are displayed against each chat message in the transcript slider. Enriched Chat Transcript 2 Enriched Chat Transcript 3 Feedback User Type Label For conversations where the customer responded to a feedback survey, a feedback user type label is automatically added based on analytics data. This label indicates whether a customer is a promoter or a detractor. Hovering over the label shows:
  • Number of feedback responses collected.
  • Type of feedback survey.
  • Customer type (determined after feedback is submitted).
  • Feedback score.
Feedback User Type Label

​
User Details

  1. Click either Conversation Summary or Conversation Event on the dashboard.
  2. Click the User Details tab to view:
    1. User ID: Unique ID assigned to the agent.
    2. Channel Data: The conversational channel where the interaction occurred.
    3. Total Conversation Sessions: Total conversations handled by the agent in the selected period.
    4. Sessions in the Last 30 Days: Conversations handled within the selected period in the last 30 days.
    5. Last Interaction Date: Date of the agent’s most recent interaction.
    6. User Meta tags: Keywords used to identify important information in the conversation.
    User Details

​
Chat History

The Chat History panel displays the full conversation flow between the AI Agent and the customer, including events, actions, input requests, queries, and intent-based responses. Failed tasks and exceptions are also shown. To view Chat History:
  • Click an entry under Conversation Summary or an event under Conversation Events on the Conversation History dashboard.
  • The Chat History window displays the conversation flow, along with:
    • Date Filter dropdown to select the period of Chat History. Chat History 1
    • Date-wise summary of:
      • Conversation channel
      • Chat initiation event
      • Chat duration
      • Chat start time and end time
      • Conversation summary (user messages, AI Agent messages, intents identified, intents unidentified, tasks completed, failed tasks)
      • Language
      • Event labels tagged to the conversation
      Chat History 2
    • X-Trace Id: A unique ID assigned to each incoming message, included in all platform logs.
    • K-Trace Id: Kore’s monitoring trace ID, useful for debugging.
    Hover over a message to see the info icon. Click the Info icon to view the Message ID associated with that message. Chat History 3 Click the Message ID to view the X-Trace Id and K-Trace Id associated with the message. Chat History 4
X-Trace Id and K-Trace Id are retained in logs for 30 days. After expiry, a tooltip displays: “Trace records for this message are not available.”

​
Define Alternate Text for JavaScript Messages

AI Agent designers can add context-specific Alternate Text to JavaScript messages or templates. This text appears alongside the JavaScript message tag in the Chat History window to clarify the message’s purpose. The Conversation History API response includes a messages.tags.altText parameter that captures the configured Alternate Text values. How it works:
  1. Use the predefined function tags.addAlternateText("value") to add Alternate Text to a JavaScript message or Web SDK template.
  2. Provide a descriptive value, for example: tags.addAlternateText("Accounts Selection Message").
Example: For a bank account creation task that renders a template prompting account type selection, the developer can generate Alternate Text like “Accounts Selection Message” in the template code. JS template editor After the user selects an account type, the Alternate message appears in Chat History above the {} JavaScript tag. Chat history alternate message Important considerations:
  • Static and dynamic values can be used for Alternate Text.
  • Alternate Text can be defined for JavaScript messages in user prompts, error prompts, Small Talk, standard responses, FAQs, and events.
  • When multiple Alternate Text values are added to a message, the platform assigns the latest value.
  • In Chat History, the platform substitutes the payload label with the Alternate Text tag for all channel templates except the SDK Template.

​
Message Tags

Message tags help identify and categorize messages in the chat transcript. They add clarity and context to conversations and can be reused across related conversations. System-defined tags are available by default. Custom tags are defined as key-value pairs, where the key is an identifier and the value is the expected customer response.
  • You cannot add the same key to a message more than once.
  • A custom message tag can only be added or detached from a message, not edited.
To add a custom message tag:
  1. Hover over the message in the transcript where you want to add the tag.
  2. Click +Message Tag. Message Tags 1
  3. In the Add Message Tag window, enter the Key and Value. Message Tags 2
  4. Click Save. The new tag appears below the message in the transcript slider. Message Tags 3
Custom message tags you create are available in the Custom Tags Filters section as filtering criteria.
Feedback Survey in Chat History If the Feedback Survey feature is enabled, the customer’s response to the survey appears in the chat transcript under Chat History. The system captures and displays a feedback event label "End of Conversation: Survey Type" indicating the end of the conversation and the survey type. Responses are mapped to a key-value pair for the conversation timeline, useful for analyzing conversation quality and customer experience. Feedback Survey The Conversation Summary displays the following on a Feedback event:
  1. Start Time and End Time, along with real-time counts for:
    • User Messages
    • AI Agent Messages
    • Intents Identified
    • Intents Unidentified
    • Tasks Completed
    • Failed Tasks
    Conversation Summary 1
  2. The Feedback Event based on the event timeline with Key and Value.
  3. The total number of feedback responses collected for the session, including:
    • Type of Feedback
    • Feedback response
    • Score