Generative AI Features - Agent 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 supportecd models.
(✅ Supported | ❌ Not supported)
Feature | Azure OpenAI Models | OpenAI Models | Custom LLM | XO GPT |
---|---|---|---|---|
Agent Coaching | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
Conversation Summary | ❌ | ❌ | ✅ | ✅ |
Generating Opposite Utterance Suggestions | GPT-3.5 Turbo | GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4o and GPT-4o mini | ✅ | ❌ |
Generating Similar Answer Suggestions | ❌ | GPT-3.5 Turbo, GPT-4, and GPT-4o mini | ❌ | ❌ |
Generating Similar Utterance Suggestions | GPT-3.5 Turbo | GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4o and GPT-4o mini | ✅ | ❌ |
Sentiment Analysis | GPT-4o | GPT-4o and GPT-4o mini | ✅ | ❌ |
Agent Coaching¶
Generate agent best responses based on the conversation history and current message to support agent coaching. Learn more.
Conversation Summary¶
Generate LLM-based summaries of conversations that have transpired up to that moment. This can be triggered upon arrival of conversation with an agent, transfer of conversation between agents, and at wrap-up of conversation, providing comprehensive wrap-up summaries.
Generating Opposite Utterance Suggestions¶
Use LLM models for generating opposite utterances during design time.
Generating Similar Answer Suggestions¶
Use LLM models for generating similar answers during design time based on semantic similarity.
Generating Similar Utterance Suggestions¶
Use LLM models for generating similar utterances during design time based on semantic similarity.
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 conversation analysis.