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.
Topic Discovery is an analytics dashboard that helps QA managers, supervisors, and CX teams analyze conversation trends through interactive visualizations and actionable insights.
It converts conversation data into actionable insights to help identify recurring issues, monitor sentiment and resolution trends, and support data-driven coaching and process improvements.
The dashboard supports Inbound and Outbound interaction analysis through the Channel filter. When applied, all topic visualizations, metrics, and conversation data update based on the selected interaction direction.
Why Use Topic Discovery?
| Challenge | How Topic Discovery Helps |
|---|
| Theme Discovery | Identifies recurring conversation topics and patterns across interactions. |
| Emerging Issues | Detects new customer issues early before they escalate. |
| Performance Trends | Tracks sentiment, resolution, and AHT trends by topic. |
| Coaching Focus | Highlights low-performing topics for targeted coaching. |
| Topic Analysis | Supports drill-down analysis from topic trends to individual conversations. |
| Taxonomy Expansion | Discovers AI-generated themes outside the configured taxonomy. |
Key Capabilities
- Topic Performance Analysis: Analyze topics using sentiment, resolution, and AHT metrics.
- Advanced Filtering: Filter data by channel, direction, language, queue, and agent.
- Intent Comparison: Compare configured intents with AI-generated topics.
- Trend Drill-down: Move from topic-level trends to individual conversations.
- Hierarchical Topic Analysis: Track trends across L1, L2, and L3 topic levels.
- Coaching Support: Identify low-performing topics for targeted coaching and process improvement.
- Proactive Detection: Surface emerging issues early through AI-generated themes.
- Direction-aware Analysis: Filter all topic visualizations, metrics, and conversation lists by contact direction (Inbound or Outbound) within each channel.
Access Topic Discovery
Navigate to Quality AI > Analyze > Topic Discovery.
Topic Hierarchy
Topic Discovery uses a three-level structure:
| Level | Description | Example |
|---|
| L1 | Top-level theme | Billing Issues |
| L2 | Subtopic under L1 | Payment Problems |
| L3 | Granular subtopic under L2 | Credit Card Declined |
Filters
The Top Filter Bar is the central control for customizing the Topic Discovery view. Every adjustment instantly updates the visualization.
| Filter | What it does | How to use it | When to use it |
|---|
| Search Topic Names | Locate topics in the visualization. | Start typing a keyword, and matching topics highlight instantly. | When looking for a specific issue (for example, “Payment Failure”). |
| Configured or Generated Intents | Switch between taxonomy-based topics and AI-discovered themes. | Select Configured Intents for your taxonomy and Generated Intents for blind spots. | Use Generated Intents to find new themes outside your taxonomy. |
| Time Range | Adjust the analysis period. | Options: 7 days (default), 28 days, 30 days, 90 days, custom. | Compare weekly vs. monthly trends to spot recurring issues. |
| Sentiment | Focus on conversations by sentiment. | Adjust the score range slider (0-10). The default is full range. | Narrow to low-sentiment conversations for quality monitoring. |
| Resolution | Filter by resolution success rates. | Adjust the score range slider (0-100). The default is full range. | Zero in on unresolved or low-resolution conversations. |
Advanced Topic Filters
Select Filters to access additional filtering options and refine the dashboard view.
| Filter | Options |
|---|
| Channel | Filter by Voice or Chat or with additional selection for Inbound and Outbound interactions. |
| Language | Multi-select with search to select one or more languages, and allows removing individual selections or clearing all. |
| Queue | Narrow by specific queues, and the Agent filter updates automatically. |
| Agent | Search and select one or more agents based on selected queues. |
| AHT | Set minimum and maximum values in seconds or define an acceptable variance range. |
Bubble Visualization Canvas
Topics are displayed as color-coded bubbles to help analyze conversation volume, performance metrics, and topic relationships.
Bubble Attributes
Each bubble encodes key topic attributes visually:
| Attribute | Meaning |
|---|
| Size | Conversation volume — larger bubbles = more conversations. |
| Color | Topic performance based on the selected metric (sentiment or resolution). |
| Position | Groups related topics together to reveal patterns and clusters. |
| Labels | L1 topics: labels outside. L2 and L3: labels appear inside. |
Sentiment Color Coding
L3 sentiment aggregates to L2/L1 with color-coded trends.
| Color | Sentiment |
|---|
| Green | Positive |
| Grey | Neutral |
| Red | Poor |
Resolution Color Coding
Topics use color codes by resolution rate, supporting combined analysis with sentiment.
| Color | Resolution Rate |
|---|
| Red | 0-50% (Low) |
| Grey | 50-70% (Moderate) |
| Green | 70-100% (High) |
Hovering over a bubble shows a tooltip with key metrics for quick assessment and deeper analysis without leaving the main view.
| Field | Description |
|---|
| Topic Name | Full name if truncated in the visualization. |
| Conversation Count | Total interactions for that topic. |
| Total Conversations | Conversation counts with trend indicators (spikes or dips in percentage). |
| Average Sentiment | Overall sentiment score with trend analysis. |
| Sentiment Breakdown | Distribution across positive, neutral, and negative interactions. |
Topic Discovery provides two topic views to support different analysis needs.
| View | Description | When to Use |
|---|
| Configured Intents | Displays topics based on your organization’s predefined taxonomy and trained conversation categories. | Use for monitoring known business categories, tracking taxonomy performance, and comparing historical trends. |
| Generated Intents | Uses AI to automatically discover conversation themes that may not exist in the configured taxonomy. | Use for identifying blind spots, detecting emerging issues, exploring unexpected conversation patterns, and expanding the taxonomy. |
Topic View Detail Pane
Select View Details from any bubble tooltip to open the detail pane for comprehensive analytics on a specific topic.
The detail pane provides topic-level analytics, trend insights, and conversation-level drill-down.
Overview Tab
Shows the Overview tab to analyze topic performance over time.
Time Granularity
Daily displays day-by-day trends for short-term monitoring, while Weekly aggregates data into weekly trends for pattern analysis.
Topic Metrics
| Metric | Description |
|---|
| Total Conversations % | Topic’s share of all conversations. |
| Average Sentiment Score | Overall sentiment with trend analysis. |
| Sentiment Breakdown | Distribution across emotional categories (Positive, neutral, and negative). |
| Average Handle Time (AHT) | AHT trend for the selected topic. |
| Average Resolution % | Resolution success rate analysis. |
| Top Keywords | Most frequent terms in topic conversations. |
| Emotion Detection | Top 6 emotions identified in conversations. |
Conversations Tab
Shows the Conversations tab with list and detailed views of interactions for analysis of the selected topic.
Conversation List Columns
| Column | Information | Purpose |
|---|
| Agent Name | Name | Identify the conversation handler. |
| Channel | Voice or Chat | Understand the interaction method. |
| Queue | Service category | Context for conversation type. |
| Actions | Conversation details | Access full interaction details. |
Navigation and Access
Full Conversation View
Select a conversation from the Conversations tab to open the full interaction view.
Conversation Details
| Section | Content |
|---|
| Complete Thread | Full customer-agent interaction. |
| Topic Highlighting | Topic markers within the conversation. |
| Metadata | Channel, duration, resolution status, sentiment scores. |
| Timeline View | Chronological conversation flow. |
| Context | Queue, agent, and channel details. |
| Tool | Description |
|---|
| Sentiment Score | Sentiment throughout the conversation. |
| Empathy Score | Empathy throughout the conversation. |
| Crutch Word Score | Crutch word usage throughout the conversation. |
Use Case: Identifying Agent Coaching Opportunities
Scenario: A QA Manager notices increasing customer complaints and needs to find specific areas for improvement.
Step-by-Step
-
Initial analysis
- Open Topic Discovery with the default 7-day view.
- Scan L1 topics for large bubbles with negative sentiment.
- Identify “Technical Support” as a high-volume, low-sentiment topic.
-
Drill-down investigation
- Select “Technical Support” to reveal L2 topics.
- Notice “Software Installation” has poor resolution rates.
- Select “Software Installation” to see L3 subtopics.
- Identify “Driver Installation” as the primary problem area.
-
Detailed analysis
- Open the “Driver Installation” detail pane.
- Metrics: 150 conversations, 45% resolution rate, average sentiment: 2.
- Top keywords:
error, crash, incompatible, frustrated.
- Top emotions: Anger (40%), Frustration (35%), Confusion (25%).
-
Conversation review
- Select View Conversations to review individual interactions.
- Review 3-4 representative conversations to identify failure patterns.
- Identify knowledge gaps in driver troubleshooting procedures.
-
Action planning
- Develop a targeted training module on driver installation.
- Create job aids for common driver compatibility issues.
- Schedule coaching sessions with agents handling technical support.
Outcome: Focused coaching based on data-driven insights leads to improved resolution rates and customer satisfaction.
