Quality AI

Automated quality management and conversation analysis.

---

Overview

Quality AI enables you to:

• Evaluate 100% of customer interactions.
• Identify coaching opportunities automatically.
• Monitor compliance and adherence.
• Drive continuous improvement with data.

---

How It Works

┌───────────────────────────────────────────────────────┐ │ Customer Interactions │ │ (Voice, Chat) │ └───────────────────────────┬───────────────────────────┘ │ ▼ │ ┌───────────────────────────────────────────────────────┐ │ Quality AI Engine │ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ Speech/ │ │ Evaluation │ │ Insight │ │ │ │ Text │ │ Scoring │ │ Generation │ │ │ │ Analysis │ │ │ │ │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ └───────────────────────────┬───────────────────────────┘ │ ┌──────────────────┼──────────────────┐ │ │ ▼ ▼ ▼ │ ┌────────────────┐ ┌───────────────┐ ┌────────────────┐ │ Auto-Scores │ │ Coaching │ │ Compliance │ │ & Evaluations │ │ Assignments │ │ Monitoring │ └────────────────┘ └───────────────┘ └────────────────┘

---

Evaluation Criteria

Standard Criteria

Pre-built evaluation criteria available out of the box:

Criteria	Description
Greeting	Proper introduction and identification
Empathy	Acknowledging customer emotions
Issue understanding	Correctly identifying the problem
Resolution	Providing an accurate solution
Closing	Proper wrap-up and next steps
Compliance	Following required disclosures

Evaluation Forms

Group criteria into evaluation forms and apply them to queues:

Form: Customer Service Standard
Criteria:
  - greeting (10%)
  - empathy (15%)
  - issue_understanding (20%)
  - resolution (30%)
  - product_knowledge (15%)
  - closing (10%)
Pass threshold: 80%
Apply to:
  - queue: support
  - channel: all

Auto-Scoring

How It Works

AI evaluates interactions in four steps:

1. Speech/text analysis — Transcribe and analyze the conversation.
2. Criteria matching — Map conversation content to evaluation criteria.
3. Scoring — Assign scores based on evidence found.
4. Confidence flagging — Flag low-confidence scores for human review.

---

Conversation Mining

Topic Analysis

Automatically identify and track conversation topics:

Analysis	Description
Topic clustering	Group conversations by theme
Sentiment by topic	Track sentiment for each topic
Volume tracking	Monitor topic frequency

​Taxonomy Builder​

Create Taxonomies

Define and manage a structured topic hierarchy for consistent, business-relevant conversation analysis:

Taxonomy: Customer Interaction Analysis
├── Communication (L1 - Strategic)
│   ├── Call Handling (L2 - Product/Service Category)
│   │   ├── Clarity (L3 - Customer Contact Reason)
│   │   ├── Tone (L3 - Customer Contact Reason)
│   │   └── Active Listening (L3 - Customer Contact Reason)
├── Knowledge (L1 - Strategic)
│   ├── Product (L2 - Product/Service Category)
│   │   ├── Features (L3 - Customer Contact Reason)
│   │   └── Pricing (L3 - Customer Contact Reason)
├── Problem Solving (L1 - Strategic)
│   ├── Issue Diagnosis (L2 - Product/Service Category)
│   │   ├── Solution Accuracy (L3 - Customer Contact Reason)
│   │   └── Efficiency (L3 - Customer Contact Reason)
└── Compliance (L1 - Strategic)
    ├── Legal & Regulatory (L2 - Product/Service Category)
    │   ├── Disclosures (L3 - Customer Contact Reason)
    │   └── Data Handling (L3 - Customer Contact Reason)

Analytics

Reports

View	Description
My Dashboard (Agent)	Assigned evaluations, sentiment trends, and resolution effectiveness
Supervisor View (Agent-Specific)	Per-agent insights with sentiment, resolution quality, and L3 topic analysis
Agent Dashboard (Supervisor Evaluation)	Language-specific, recent evaluation data for coaching

Dashboards

Quality Dashboards

• Agent Performance Report: Scores, pass/fail, metric adherence, coaching assignments.
• Interaction Evaluation & Conversation Analytics Report: Sentiment, topics (L3), agent metrics, evaluation outcomes.
• Evaluation Form Summary Report: Metric adherence, compliance stats, fatal violations, overall trends.

Setup Quality AI

Complete these steps to get Quality AI running.

1. Configure Permissions

• Go to User Management > Role Management > New Role > Other Modules. Learn more.
• Assign the Supervisor role or create custom roles with QM permissions. Learn more.

2. Set Up Contact Center

• Assign Supervisors and Auditors to the relevant queues so they can access the right interactions. Learn more.

3. Enable Features

• Enable Conversation Intelligence, Auto QA, and Bookmarks in Quality AI Settings. Learn more.
• Enable Answer and Utterance suggestions in GenAI Settings. Learn more.

4. Create Evaluation Metrics

• Choose a measurement type: By Question, Question Answer Pair, or Adherence (Static or Dynamic). Learn more.
• Create evaluation metrics. Learn more.
• Set the count type: Entire Conversation or Time Bound. Learn more.

5. Create Evaluation Forms

• Assign a name, description, channel, and pass score.
• Select metrics, assign weights, and link the form to queues. Learn more.

​6. Configure Agent Scorecards

• Enable Agent Scorecards in Quality AI Settings.
• Create agent attributes using evaluation metrics.
• Create scorecards, assign attributes and weights.
• Assign scorecards to agents or groups and set a default scorecard. Learn more.

7. Configure Taxonomy

• Create L1, L2, and L3 topics for conversation classification.
• Enable or adjust resolution tracking for L3 topics.
• Save and version taxonomy changes. Learn more.

8. Analyze Interactions in Conversation Mining

• Use filters to review scored interactions. Learn more.
• Save filters to reuse them in audit assignments. Learn more.

9. Create Audit Allocations

• Assign interactions to auditors for manual evaluation.
• Create allocations with filters and sampling.
• Assign interactions to auditors.
• Evaluate interactions using assigned forms.
• Use AI-assisted audits and navigation. Learn more.

10. Run AI-Assisted Manual Audits

• Use AI-assisted audits for faster, more consistent scoring.
• Navigate interactions using adherence moments and violations. Learn more.

11. Monitor Performance

• Use the Dashboard to track individual QA progress and queue statistics. Learn more.
• Use the Conversation Intelligence Dashboard for contact center-wide performance trends. Learn more.

---