Conversational Intelligence Configuration

The Conversational Intelligence screen is where you configure the automated topic clustering and category classification that powers the Categories & Themes insights.

This guide covers how to create taxonomies (your own category structures) and configure the topic/theme clustering that automatically discovers what customers are asking about.

Accessing the Screen

Navigate to Conversational Intelligence from the main admin menu. This screen has two main tabs:

1. Topics & Themes — Configure and run the automated clustering analysis
2. Taxonomies & Categories — Define your own category structures for governed classification

Topics & Themes Tab

The Topics & Themes tab is where you configure and monitor the automated clustering that discovers what customers are asking about.

Enabling Clustering

The Enable Topic & Theme Clustering toggle controls whether clustering runs for this service:

• Enabled — Questions are automatically clustered into topics and themes after each scheduled crawl completes
• Disabled — Clustering is paused; no new analysis runs will occur

This setting saves automatically when changed. Disabling clustering does not delete existing themes — it simply stops new analysis runs. You can re-enable it at any time.

Note: Clustering is tied to your crawl schedule. When a scheduled crawl completes successfully, clustering automatically runs if enabled. This ensures clustering always has the freshest content available. If you don't have a crawl schedule configured, you can trigger analyses manually.

Analysis Status

Below the toggle, you'll see:

• Last Analysis — Status badge (Completed/Running/Failed) with the date range and question count
• Analysis Month — Dropdown to select which month to view or analyse

Running a New Analysis

Click + New Analysis to trigger clustering for the selected month. This is useful when:

• You've just set up the service and want initial themes
• You've made significant changes to your content
• You want to refresh the current month's preliminary data

Resetting Themes

Click Reset Themes to delete all existing themes and clustering history. After resetting, run a new analysis to create fresh themes based on your current data.

Warning: This action cannot be undone.

Advanced Clustering Settings

Expand the Advanced Clustering Settings section to adjust clustering behaviour. For most use cases, the defaults work well.

Warning: Changing these from defaults will likely have a detrimental impact on clustering quality unless you have a specific reason to adjust them.

These settings apply to the next analysis run.

Taxonomies & Categories Tab

A taxonomy is a classification system you define to organise customer questions according to your business structure. Unlike themes (which are discovered automatically), taxonomies give you governed, consistent categories that align with your organisation.

Why Use Taxonomies?

• Business alignment — Categories match your departments, products, or service areas
• Ownership — Assign owners to categories for reporting and accountability
• Consistency — The same categories apply across time, making trends comparable
• Multiple views — Create different taxonomies for different stakeholders (e.g., by department vs. by enquiry type)

Creating a Taxonomy

1. Click New in the Taxonomies card
2. Configure the taxonomy settings:

1. Click Save to create the taxonomy in draft status

Category Types

Choose the type that best describes your categories:

• Departments — Organisational units (e.g., Economics, Law, Medicine)
• Topics — Subject areas (e.g., Billing, Returns, Shipping)
• Products — Product or service lines (e.g., Widget A, Service B)
• Intents — User goals (e.g., Buy, Ask, Complain)
• Regions — Geographic areas (e.g., North, South, International)
• Priorities — Urgency levels (e.g., Urgent, Normal, Low)
• Custom — Define your own type

Adding Categories

After creating a taxonomy, switch to the Categories tab to add your classification labels.

1. Click Add Category
2. Fill in the category details:

1. Click Save Category

Training Sources

Each category can have training sources that help the AI understand what belongs there. Click on a category row to see and manage its training sources.

Training source types:

The more training data you provide, the more accurate the classification becomes.

Publishing a Taxonomy

Taxonomies start in Draft status, allowing you to refine them before use.

When ready:

1. Ensure all categories have been added
2. Review your training sources
3. Click Publish

The system will:
1. Build training data from your sources (progress shown in the header)
2. Generate semantic embeddings for each category
3. Make the taxonomy available for classification

Once published, certain settings become locked to maintain classification stability. A notice will appear explaining which settings can still be edited:

• Editable: Taxonomy name, category type (for your records), and each category's name, owner, and email
• Locked: Assignment mode, hierarchy, training sources, and descriptions

To change locked settings, you'll need to create a new version.

Creating a New Version

If you need to change locked settings on a published taxonomy:

1. Click New Version to create an editable draft based on the published taxonomy
2. Make your changes
3. Publish the new version

The new version will replace the previous one for future classifications.

Running Classification

Once published, click Classify Conversations to:

• Classify all unclassified questions against your taxonomy
• Optionally re-classify all questions (check "Re-classify all questions")

Classification also runs automatically on a daily schedule (04:00 UTC).

Quality and Review

Each taxonomy has several tabs for monitoring performance and reviewing classifications.

Reports Tab

The Reports tab shows quality metrics and assignment summaries.

Quality Metrics

Assignment Summary

Shows how many questions have been assigned to each category, broken down by:

• Suggested — Automatically classified, pending review
• Below Threshold — Best match, but confidence didn't meet the threshold
• Confirmed — Human-verified as correct
• Rejected — Human-corrected to a different category
• Total — Sum of all assignments

Categories Tab

Lists all categories in the taxonomy with:

• Label — Category name
• Parent — Parent category (if hierarchical)
• Status — Active or Inactive
• Order — Display sort order
• Training Data — Number of training examples

Click the action icons to view questions, review assignments, or edit the category.

Near Matches Tab

Shows questions where two or more categories scored nearly identically (within 4%). The top scorer was assigned, but you may want to review these to:

• Confirm the correct assignment (click Confirm)
• Mark as incorrect (click Doesn't Fit)
• Change the assigned category using the dropdown

These borderline cases reveal where categories overlap and can be used as training examples to improve accuracy.

Unassigned Tab

Shows questions that didn't meet the confidence threshold for any category. Each item displays:

• The question text
• Suggested categories — Top matches with confidence scores
• Assign to — Dropdown to manually assign

These may represent:

• Gaps in your taxonomy
• Questions too generic to classify
• New topics you haven't accounted for

Click Confirm to assign a question to the selected category.

How Clustering Works

Each month, the system:

1. Collects all questions from conversations
2. Uses AI to identify semantically similar questions
3. Groups them into clusters — collections of very similar questions
4. Maps clusters to persistent themes for tracking over time

This happens automatically after each scheduled crawl completes, but you can also trigger manual analyses from the Topics & Themes tab.

Note: Because clustering runs monthly, date range filters on the Categories & Themes dashboard may not be exact when filtering topic clusters and themes. The clusters represent the full month's data regardless of the date range selected.

Automatic Scheduling

Clustering and classification run automatically based on your crawl schedule:

Crawl-Triggered Clustering

When a scheduled crawl completes successfully, the system automatically:

1. Checks if clustering is enabled — Via the toggle on this screen
2. Runs clustering — Groups new questions into clusters and maps them to themes
3. Limits to once per day — If a service is crawled multiple times daily, clustering only runs after the first successful crawl

This ensures clustering always has the freshest indexed content available.

Daily Classification

Classification runs daily at 04:00 UTC for all services with published taxonomies. This means new questions are typically classified by early morning each day.

Manual Runs

You can also trigger clustering or classification manually at any time:

• Clustering — Click + New Analysis on the Topics & Themes tab
• Classification — Click Classify Conversations on a published taxonomy

Best Practices

Designing Taxonomies

1. Start with your org structure — Categories should reflect how you naturally think about your business
2. Keep it manageable — Start with 10-20 categories; you can always add more
3. Use hierarchy sparingly — Deep hierarchies can be harder to manage
4. Write clear descriptions — Help the AI understand what belongs in each category
5. Add training examples — A few exemplar questions significantly improve accuracy

Improving Classification Accuracy

1. Review near-matches — These borderline cases reveal where categories overlap
2. Add negative exemplars — Help distinguish similar categories
3. Check unassigned questions — May reveal gaps in your taxonomy
4. Provide feedback — Use thumbs up/down on classified questions to train the system

Monitoring Themes

1. Watch for emerging themes — New clusters may indicate new issues or opportunities
2. Track theme trends — Declining themes may indicate successful interventions
3. Review theme descriptions — AI-generated labels usually capture the intent well
4. Use themes alongside taxonomies — Themes discover what you didn't anticipate; taxonomies track what you planned for

Related Documentation

• Categories & Themes — Using the insights dashboard
• Customer Service Insights — Overall insights overview
• Insights Overview — Getting started with analytics

← Back to Insights overview