...
Sentiment Analysis: Detects emotions in conversations, displaying icons for happy, neutral, or angry tones.
Entity Extraction: Identifies useful data such as:
Automatic CRM or ticket system link generation based on customer or ticket numbers.
Suggested transaction codes related to the call.
Summary extraction at the end of the call.
- Transaction Code Suggestions: based on the conversation context.
- The AI can detect relevant transaction codes during the call.
- Suggested transaction codes are displayed to the agent in real-time.
AI Pipeline Integration: Supports multiple AI models, including:
Microsoft Copilot
Existing chatbots
Custom AI solutions with REST API support.
Parallel AI Processing: Multiple AIs can process data simultaneously without delays.
...
They Can be assigned per role (Client Admin / Client User).
AI Service Rendering Control
It is possible to control the rendering (visibility) of individual Live Agent AI services via dedicated resources.
Each AI feature (Transcription, Assistant, Sentiment, Suggestions, etc.) has a separate permission resource.
| Resource | Description |
|---|---|
| Renders the AI Transcription section. |
portal.AgentHome.LiveAgent.AI.Assistant | Renders the AI Assistant services (Suggestions, Summary, Sentiment). |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.Caller | Renders the caller's sentiment analysis. |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.Agent | Renders the agent's sentiment analysis. |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.Sugesstion | Renders the AI Suggestion section. |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.Summary | Renders the AI Summary section. |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.Satisfaction | Renders the AI Satisfaction section. |
portal.Acd.AgentHome.LiveAgent.AI.Assistant.TAC | Renders the AI Transaction Code section. |
Client Master Data - Parameters
In Client Master Data - Parameters. set AI Pipeline Configuration, After Call Pipeline Configuration and Transcription Provider
| Name | Value |
|---|---|
LiveAgent.AIPipeline.EndPoint | http://<server>:<port>/api/v1/aipipeline |
LiveAgent.AIPipeline.Input | { "endpoints": [ { "type": "suggestions", "url": "http://<server>:<port>/webhooks/rest/webhook", "input": { "sender": "%Service.StatisticsPartAID_%", "message": "$ai_pipeline_input" } }, { "type": "sentiment", "url": "http://<server>:<port>/api/v1/sentiment", "input": { "data": "$ai_pipeline_input" } } ]} |
LiveAgent.AfterCallPipeline.EndPoint | http://<server>:<port>/api/v1/aftercall |
LiveAgent.AfterCallPipeline.Input | { "endpoints" : [ { "type" : "summary", "url" : "http://<server>:<port>/api/v1/summary", "input" : $ai_pipeline_input } ], "respondTo" : { "host" : "%SERVER_IP_UDP_ADDRESS%", "port" : %ACD.UDP.Webserver.Port%, "message" : "NONCALL;AI_AFTERCALL_PIPELINE_RESULT;%QueueCheck.AgentDataID%;%Service.StatisticsPartAID_%;AI_PIPELINE_OUTPUT=$ai_pipeline_output" }} |
| # Instructions
|
| # Instructions
|
| # Instructions
|
| # Instructions
|
LiveAgent.Transcribe.Provider | EnderTuring.v2 (or Azure...) |
User Settings
Activate Live Agent functionality per user role:
...