Conversation Mining enables supervisors to review, analyze, and filter scored conversations, centralizing insights into quality, agent performance, customer experience, and ingested metadata. Users with Cross Queue Data Access can view interactions and evaluation forms across all queues (including newly added ones), while others are limited to assigned queues. Users with Download Conversations can download recordings and transcripts from the Audit screen for offline use. Supervisors can refine results using filters such as evaluation metrics, qualification outcomes, duration status, contact direction, configured and generated intents, and custom fields. The Custom Fields filter updates dynamically based on the selected date range and supports dropdown or text input depending on the field type.Documentation Index
Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Access Interactions
Navigate to Quality AI > Analyze > Conversation Mining > Interactions.
Use the Contact Direction filter to analyze Inbound and Outbound interactions separately, alongside existing filters such as Queue, Channel, and Evaluation Form.
Key Capabilities
- Review and Filter Interactions: Analyze scored conversations to identify coaching or follow-up opportunities; supports cross-queue access based on permissions.
- Monitor Conversation Quality: Track quality, agent performance, and customer experience at conversation and agent levels.
- Gain Deeper Insights: Leverage taxonomy-based topic discovery, topic-level sentiment, and resolution insights across Conversation Mining, AI-Assisted Audit, and Agent Dashboards.
- Identify Key Insights: Use topics, sentiment, and resolution indicators to surface high-impact or unresolved conversations.
- Filter by Experience Insights: Apply filters such as configured intents (L1–L3), generated intents, resolution status, duration status, and contact direction.
- Audit with Precision: Customize views with metadata and column controls, including intent, sentiment, resolution, duration, and direction.
- Search Conversations: Use keyword search with include or exclude logic and speaker-based options.
- Navigate by Timeline: Jump to relevant moments with timeline-based search and match navigation.
- Save Custom Views: Store reusable filter sets and column configurations for consistent analysis.
Conversation Interaction Details
The following interaction details are available for each conversation.| Column | Description |
|---|---|
| Agents | Shows the name of the agent who last handled and ended the interaction. - Channel and Direction: Displays the channel and contact direction—for example, Voice or Chat: Inbound or Outbound. |
| Processing Status | Indicates overall processing outcome—green for success and red for failure. Includes Auto QA checks (question adherence, value adherence, hold inference) and Conversation Intelligence outputs (sentiment, topics, intents, and taxonomy-based insights). |
| Actions | Provides quick actions for the interaction, such as audit, bookmark, and evaluation status indicators. |
| Queues | Shows the queue assigned to the interaction. The system uses this queue to select the evaluation form for scoring. |
| Kore Evaluation Score | Displays the Auto QA score based on the assigned evaluation form. Hover to view statuses such as Pass, Failed, Minimum Duration Threshold, or Manual Evaluation Metrics Excluded. Excluded Interactions: Interactions excluded from scoring (manual metrics, below threshold, or unavailable duration) remain available in Conversation Mining for review, including Audit, Conversation Details, and Logs. |
| Sentiment Score | Displays the customer sentiment score derived from the conversation. |
| Supervisor Audit Score | Displays the supervisor-assigned score for audited or manually evaluated interactions and highlights manual evaluation metrics (fatal metrics count) with a consistent visual indicator. |
| Start Time | Displays conversation start time (for example, 24 May 2024, 1:17:10 PM). |
| Duration | Displays the call duration, including talk time, hold time, and ACW (for example, 0h 6m 25s). |
| Moments | Displays detected conversation moments, including Questions Adherence (met metrics), Violations (speech-based issues), and Omissions (unmet metrics such as playbook steps, dialog tasks, and question-level checks). Select an interaction to open the conversation history and view Moment metrics in the AI-Assisted Manual Audit page. Learn more |
| Sentiment Trend | Shows the distribution of positive, negative, and neutral tones, tracks sentiment changes during the call, highlights the resolution tone, and summarizes overall sentiment. |
| Emotions | Shows customer emotional states or tracked emotions during a conversation. |
| Conversation ID | Displays the user-defined identifier for custom tracking. |
| Custom Conversation ID | Unique system-generated identifier used as the primary key. |
| Configured Intents | Displays mapped intents across levels (L1, L2, L3) with sentiment indicators and uses a color-coded map (red, green, gray) to indicate the sentiment of each detected topic. |
| Overall Resolution | Indicates if the interaction is resolved or unresolved based on whether all L3 intents are addressed. |
| Generated Intents | Displays the AI-generated intents in each conversation. Displays No form assigned for conversations skipped due to missing direction-specific forms. |
| Contact Direction | Displays inbound or outbound interaction type |
| Evaluation Status | Displays No form assigned for conversations skipped due to missing direction-specific forms. |
You must enable bookmarks in the Settings before tagging interactions for future reference.
Filter Interactions
Use filters to locate conversations, evaluate agent performance, and support quality analysis.Columns
Select this filter to include or exclude specific fields in the Interactions dashboard.Bookmarks
Assign interactions to bookmarks and view all bookmarks linked to a specific interaction.Filter Panel Actions
- Apply: Applies filters immediately.
- Save & Apply: Saves and applies filters.
- Clear: Resets all filters.
- Cancel: Closes the panel without applying changes.
Add New Filter
Select Filters > + Add New Filter, then choose a category such as Efficiency, Experience, Behavior, Keywords, or Custom Fields to refine results.Filter Categories
Filter by Efficiency
Filters interactions based on handling metrics and process adherence.- Select Channel (Chat or Voice) and Direction (Inbound or Outbound) to filter interactions by communication type; applying these filters dynamically updates interaction counts and dashboard metrics.
- Select an Audit Status to filter interactions: Audited (reviewed interactions), Assigned (interactions that are not reviewed), and Not Assigned (interactions with no auditor assigned).
- Select a Duration Status to control which interactions appear based on evaluation eligibility:
- All (default): Displays all interactions regardless of duration.
- Evaluated: Displays interactions that meet the threshold and receive a score.
- Below Threshold: Displays interactions that fall below the configured threshold and are excluded from scoring.
- Duration Unavailable: Displays interactions with unresolved duration.
- Enter the Conversation ID or Custom Conversation ID to filter a specific interaction.
- From Queues, select the routing group. Users with the Cross Queue Data Access permission can select from all available queues. Other users see only their assigned queues.
- From Agent Groups, select the group linked to the chosen queue.
- From Agents, select the agent assigned to the queue.
- Configure the optional filter, such as filter by AHT (average handling time) using minimum or maximum time in seconds, or by AHT deviation, deviation %, and number of transfers.
- Enable additional filters such as handling time, AHT deviation (with %), and number of transfers to refine interactions based on efficiency metrics.
If the connectors are enabled, you can’t view AHT and number of transfers.
Filter by Experience
This category captures the emotional and qualitative aspects of the customer journey.| Filter | Description |
|---|---|
| Avg. Waiting Time | Select a date range in seconds. |
| Sentiment Score | Slider to set min-max range for positive (higher) or negative (lower) sentiment. |
| CSAT | Filter by customer satisfaction score to view and drill down into interaction distribution across score ranges based on feedback responses. |
| Configured Intents | Filter by topic/intent across L1, L2, L3. Child lists update based on parent selection. |
| Generated Intents | Select the AI-generated or configured intents based on your input. |
| Overall Resolution | Filter conversations as Resolved or Unresolved (both selected by default). Resolved indicates all applicable L3 intents are identified; Unresolved indicates at least one intent is missing. |
| Churn Monitor | Filter options under Churn Monitor: - Churn Risk: Displays the likelihood of customer churn for a conversation over a selected period, shown as a percentage. - Escalation: Tracks the number of times a customer escalated an issue to a supervisor. Select levels in order—L1, then L2, then L3. At least one level is required. All levels update dynamically based on your selections. Churn is calculated once per interaction and is not a cumulative score. |
Select Configured Intent levels in order: L1 first, then L2, then L3. You must select at least one level to apply the filter.
Filter by Behavior
This category analyzes interaction dynamics and conduct between agents and customers.| Filter | Description |
|---|---|
| Metric Name | Enables you to select a single evaluation metric (shown as a tag) and filter interactions by Pass or Fail. Manual metrics are visually indicated for audit identification. |
| Metric Qualification | Enables you to filter interactions by metric outcome. When you select a Dynamic By Question metric in the Metric Name filter, the Metric Qualification field displays three options: - Pass — Conversations where the trigger is present, and the answer matches the expected utterance (Adhered outcome). - Fail — Conversations where the trigger is present, but the answer doesn’t match the expected utterance (Not Adhered outcome). - N/A — Trigger not detected. This option is available only for Dynamic By Question metrics and filters interactions where the metric outcome is not applicable. |
| Language | Select a conversation language to add from the dropdown list. |
| Empathy Score | Measures how well the agent responds to the customer’s emotional state. A higher score indicates a more empathetic interaction. |
| Crutch Word Score | Measures the use of filler words (for example, um, uh) by the agent. A higher score indicates greater use of crutch words. |
| Agent Playbook Adherence | Displays the Agent AI playbook adherence percentage for an interaction. |
| Kore Evaluation Score | Displays the automated QA score for an interaction, based on the evaluation form assigned to an interaction’s queue. |
| Validation Failure | Displays interactions that fail validation and are not processed for evaluation. You can use Form, Channel, and Language to refine results. |
Filter by Keywords
This enables you to search, filter, and review conversations using specific keywords or phrases. You can filter by included or excluded keywords and by speaker, with results linked directly to the QA audit screen.| Category | Details |
|---|---|
| Filter by Keywords | Helps you search, filter, and review conversations using specific keywords or phrases. Supports included/excluded keywords and speaker-based filtering, with results linked directly to the QA audit screen. |
| Conditions (AND / OR) | Defines how multiple keywords in the Include section are combined. - AND: All specified keywords must appear in the conversation. Example: Include Billing AND frustrated (both speakers); Exclude Resolved (both speakers). - OR: At least one keyword must appear. Example: Include Refund OR Money Back (customer only); Exclude Processed (agent only) and Completed (both speakers). |
| Conversation Including Keywords | Search using specific keywords or exact phrases with optional speaker filters. Select speaker (Agent, Customer, or Both), enter keywords or phrases, and add up to 8 keywords using +Add Keyword. |
| Conversation Excluding Keywords | Exclude conversations containing specific keywords or phrases. Select speaker (Agent, Customer, or Both) and add up to 5 exclusions using +Add Exclude Keyword. All exclusions use AND NOT logic. |
| Audit Navigation and Filtering | Enables quick filtering and navigation by keyword or QA question, with auto-scrolling of transcripts and relevance-based matching. |
| Apply Keywords Action | Select Apply Keywords to activate filters, then Apply to run the search and view results. |
| Filtered Keywords Interactions | Displays the count of interactions matching the selected keywords (for example, Filtered Interactions: 22). |
Filter by Custom Fields
The Custom Fields filter lets you refine interactions using business-specific metadata from Express File or Agent AI integrations. Custom fields appear dynamically based on the selected date range, and interactions that don’t contain the selected field are excluded from the results. To apply a custom field filter:- Select Custom Fields from the Filter By panel.
- Select the Key from the dropdown. Example: Account ID.
- Enter the matching Value.
- (Optional) Select + Add Custom Field to include additional key-value pairs.
-
Select Apply or Save & Apply.
Conversations that don’t carry the selected custom field are excluded from results entirely.
Manage Saved Filters
Use saved filters to apply, store, and manage filter configurations on the Conversation Mining dashboard.| Action | Description |
|---|---|
| Apply Filters | Stores current settings as an Unsaved Filter. |
| Save & Apply | Saves and names filters for audit allocation; saving is optional if audits are not used. |
| Save Filters | Saves the current filter configuration with a name and optionally sets it as the default on the Interactions dashboard. |
| View Saved Filters | Shows all saved and their associated unsaved filters. |
| Filtered Interactions | Displays a real-time count of matching conversations. |
| Customization Options | Includes Copy, Mark as Default, Edit, and Delete filters. |
If interactions are not used for audit allocation, you can apply filters without saving.