Access Conversation Mining
Navigate to Quality AI > AutoQA > Conversation Mining.
Use Contact Direction together with Queue, Experience Flow, Channel, Evaluation Form, and other filters to analyze inbound and outbound interactions.
Interactions Page
The Interactions page includes two tabs:- Processed: Displays conversations that have completed Quality AI processing and are available for review, audit, and evaluation.
- Pending: Displays conversations awaiting processing or that failed validation. Successfully processed conversations move to the Processed tab.
Key Capabilities
- Review processed conversations for coaching, investigations, and quality analysis.
- Analyze evaluation scores, sentiment, topics, intents, emotions, and resolution outcomes.
- Review AI Agent, Human Agent, and AI-to-Human handoff conversations independently.
- Open the corresponding AI or Human audit segment directly from each conversation record.
- Monitor processing status (Pending, In Progress, Failed) from the Pending tab.
- Filter conversations using queues, experience flows, agents, intents, keywords, channels, contact direction, evaluation metrics, and custom fields.
- Apply experience filters such as L1/L2/L3 intents, generated intents, resolution status, and duration status.
- Customize workspace with configurable columns, saved views, and timeline navigation.
- Track review status including agent acknowledgement and dispute status for evaluated conversations.
Conversation Records
The conversation type determines the number of rows displayed.
Each record opens its corresponding audit segment.
Record Behavior
- Each evaluation segment appears as an independent record.
- Selecting a Human Agent record opens the Human Agent audit segment.
- Selecting an AI Agent record opens the AI Agent audit segment.
- AI Agent records use Experience Flow assignments.
- Human Agent records use Queue assignments.
Track Conversation Processing
Processed Tab
The Pending tab (Pending Conversations) allows you monitor the processing status of conversations submitted to Quality AI. It includes conversations that are Pending, In Progress, or Failed validation. You can’t open conversations from this tab. After Quality AI successfully processes a conversation, the system automatically moves it to the Processed tab, where you can review it in the AI-Assisted Audit screen. For AI-to-Human conversations:- Selecting the AI Agent row opens the AI Agent audit segment.
- Selecting the Human Agent row opens the Human Agent audit segment.
The Pending tab is available only when Automation AI, Agent AI, or Contact Center AI (CCAI) conversation sources are enabled for the workspace.
Access Process Tab Conversations
Navigate to Quality AI > AutoQA > Conversation Mining > Processing.
Filter by Processing Status
Supervisors use the Status filter on the Pending tab to view conversations by processing state. The filter includes the options such as Select All, Pending, In Progress and Failed.Conversation Grid Details
The Conversation Mining grid displays one record for every evaluation segment. You must create bookmarks in Settings before tagging interactions for future reference.
AI Agent Conversation Behavior
AI Agent conversation segments differ from Human Agent segments. For AI Agent conversations:- The system displays Experience Flow instead of Queue.
- The system uses AI evaluation forms.
- The system doesn’t generate speech-related moments.
- The system doesn’t generate speech metrics such as Empathy Score, Dead Air, Cross-talk, Speaking Rate, Hold, and Crutch Words.
- The system uses AI-specific evaluation metrics.
View Conversation Processing Status
The Pending tab (Pending Conversation) displays conversations with processing status as In Progress or Failed. Use this tab to monitor processing status. You can’t open conversations from the Pending tab. After Quality AI processes a conversation successfully, the system moves it to the Processed tab, where you can review it in the AI-Assisted Audit screen.
The Pending tab is available only when Automation AI, Agent AI, or Contact Center AI (CCAI) conversation sources are enabled for the workspace.
Access Pending Conversations
Navigate to Quality AI > AutoQA > Conversation Mining > Pending. The Pending tab displays the following columns: Handled By Agent, Conversation ID, Start Date, End Date, and Processing Status.Filter by Processing Status
Use the Status filter to view all Pending, In Progress, or Failed conversations.Filter Conversations
Use the toolbar at the top of the Conversation Mining page to locate and manage conversations. The filters apply to both the Processed and Pending tabs.Add New Filter
Select Filters from the Conversation Mining toolbar to open the filter panel. Select + Add New Filter, then choose a filter category. The system applies the selected filters to the current active tab (Processed or Pending).Filter Categories
The filter panel includes:Filter by Efficiency
Filter by Efficiency analyzes emotional, behavioral, and qualitative aspects of customer interactions using sentiment, interaction metadata, and operational filters.Audit Allocations
Select Audit Allocations to filter and view interactions associated with specific audit batches or allocation groups directly from Conversation Mining without manually filtering individual Conversation IDs.Duration Status
Select a Duration Status to control which interactions appear based on evaluation eligibility:Conversation Identifiers
Enter the Conversation ID or Custom Conversation ID to filter a specific interaction for targeted audit analysis and tracking.Handled AI Agent
Filters interactions handled by the AI Agent.- Experience Flow: Select or search for the AI experience flow associated with the conversation.
Human Agent
Filters interactions handled by a Human Agent.- Custom Conversation ID: Search using a custom conversation identifier.
- Queues: Select queues associated with the human-handled interaction.
- Agents: Filter by specific agents involved in the conversation.
Apply both AI and Human filters to return interactions that match either segment.
Queue-Based Filtering (Advanced Routing Filters)
Refine results using the organizational routing structure.- Select Queues to view routing groups.
- Users with Cross Queue Data Access can select all queues.
- Other users can select only their assigned queues.
- Select Agent Groups linked to the selected queue.
- Select Agents assigned to the selected queue.
Advanced Performance Filters
Enable additional performance-based filters. If the connectors are enabled, you can’t view AHT and number of transfers.
Filter by Experience
This category helps analyze emotional and qualitative aspects of customer interactions using sentiment and emotion-based filters.
You can view the CSAT and Avg. Waiting Time filter parameters only when the Connector is in disabled mode.
Filter by Behavior
This category analyzes filters based on agent conduct and interaction dynamics.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.Filter by Custom Fields
This helps to refine interactions using business-specific metadata from Express File or Agent AI integrations. Custom fields are dynamically available based on the selected date range. The system excludes interactions that doesn’t include the selected field from results. To apply a custom field filter:- Select Custom Fields from the Filter By panel.
- Select the Key from the dropdown. For 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.
Filtered Interactions: 22).
Manage Saved Filters
Use the Saved Filters UI to apply, store, and manage filter configurations on the Conversation Mining dashboard.If interactions aren’t used for audit allocation, you can apply the current filters without saving them as a reusable saved filter.