Generative AI Features - Contact Center AI¶
Utilize generative AI features to supercharge your AI Agent with powerful tools that enhance productivity, enable natural conversations, improve intent detection, analyze customer sentiment, and support agent performance, all working together to create seamless end-user experiences through intuitive design.
Model Feature Matrix¶
The following table displays the features and the supported models.
(✅ Supported | ❌ Not supported)
| Feature | Azure OpenAI Model(s) | OpenAI Model(s) | Custom LLM | XO GPT |
|---|---|---|---|---|
| Agent Empathy Identification | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Agent Response Rephrasing | ❌ | GPT-3.5 Turbo | ❌ | ❌ |
| By Value Adherence validation for Quality AI | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| By Value metric extraction for Quality AI | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Churn & Escalation Identification | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Conversation Summary | ❌ | ❌ | ✅ | ✅ |
| Crutch Word Usage Detection | GPT-4o | GPT-4o | ✅ | ❌ |
| Default Script Adherence | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| GenAI based agent answer adherence and customer trigger detection | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Generating Similar QM Utterance Suggestions | GPT-4 | GPT-3.5, GPT-4o and GPT-4o mini | ❌ | ❌ |
| Post-Interaction Sentiment Analytics and Key Emotion Moments | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Sentiment Analysis | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
| Topic Modelling | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
Agent Empathy Identification¶
Identify instances of agent empathy where customers have expressed negative sentiment through Quality AI using LLMs.
Agent Response Rephrasing¶
Agents will be able to choose the LLM to rephrase their responses in the following tones.
- Formalize: Enables agents to enhance the formality of their writing, making it suitable for business or other formal contexts.
- Friendly: Offers suggestions and improvements to promote a friendly and approachable tone in text.
- Expand: Enables agents to enhance the formality of their writing, making it suitable for business or any other formal setting.
- Rephrase: Allows agents to elevate the formality of their writing, making it suitable for business or any other formal context.
By Value Adherence validation for Quality AI¶
Validates data adherence by comparing extracted metric values against reference data using multilingual LLM analysis. Performs precise value matching and returns binary adherence scores for each metric.
By Value metric extraction for Quality AI¶
Extract by value metric from user/agent/bot messages through Quality AI using LLMs.
Churn & Escalation Identification¶
Utilize LLMs to identify agent crutch word usage in customer conversations using Quality AI.
Conversation Summary¶
Generate LLM-based summaries of conversations that have transpired up to that moment. This can be triggered upon arrival at a conversation with an agent, transfer of conversation between agents, and at the wrap-up of a conversation, providing comprehensive wrap-up summaries.
Crutch Word Usage Detection¶
Use LLMs to detect agent crutch word usage in customer conversations through Quality AI.
Default Script Adherence¶
Determine agent adherence to default script steps across greeting, branding, privacy policy, customer verification, hold etiquette, and call closing through Quality AI's conversation Intelligence dashboard using LLMs. Learn more.
GenAI-based agent answer adherence and customer trigger detection¶
Utilize LLMs to verify agent adherence and detect customer triggers without requiring configuration of utterances or training. Learn more.
Generating Similar QM Utterance Suggestions¶
Utilize LLM models to generate similar phrases during the design phase, focusing on semantic similarity. Learn more.
Post-Interaction Sentiment Analytics and Key Emotion Moments¶
Generate post-interaction sentiment and emotion moment insights for agent conversations from Quality AI using LLMs.
Sentiment Analysis¶
Agents will be able to monitor customer sentiment dynamically during active chat conversations. When enabled, this feature displays a sentiment indicator that updates in real-time based on ongoing analysis of the conversation.
Topic Modelling¶
Extract popular Topics and Intents that customers discuss across agent conversations through Quality AI using LLMs