Help Center/ Cognitive Engagement Center/ User Guide/ Tenant Administrator Guide/ Robot Management and Configuration Guide/ Large Language Model Service Zone/ LLM-based Application Services/ LLM-based Agent Assistant/ Verification
Updated on 2025-01-23 GMT+08:00
View PDF
Share

Verification

Verifying the agent assistant function by referring to this section.

Prerequisites

None

Procedure

  1. The agent accesses the audio and video workbench and clicks on the right if the voice call mode is selected. If the question reported by the customer matches a keyword in Intention Management and FAQ Management on the TUC configured in Configuring Information on the TUC, the corresponding script recommendation and FAQ recommendation are generated. Click to view the transcription result, agent's sentiment analysis result, and customer emotion.
  2. The agent accesses the online chat workbench and clicks on the right to view the customer emotion, intent, script recommendation, and FAQ recommendation if the multimedia chat mode is selected. If an agent enters sensitive words or content with negative emotions, the corresponding prompt is displayed and the content cannot be sent to the customer.

    Figure 1 FAQ recommendation
    Figure 2 Script recommendation
    Figure 3 Negative emotion

    Figure 4 Sensitive word