The dashboard in the AI Control Center provides a compact overview of the performance of the AI agents in use.It combines basic quality metrics with detailed performance metrics allowing for a quick assessment of how reliable and efficient current automations are working.
Basic AI Metrics
These metrics provide information about how reliable the AI operates in daily use.-
Customer correctly identified
Percentage of work sessions where the customer was unambiguously matched without manual intervention. -
Correctly categorized with tags
The proportion of work sessions where the AI set the correct tags. No manual intervention was required. -
Text Assistant Accuracy
Average accuracy of the text assistant, calculated over all work sessions in the selected period.
AI Performance Metrics
This shows the operational effectiveness of automation:-
Automatic processing
Indicates the number of tickets that were processed automatically, differentiated by with approval (L4) and completely autonomously (L5). -
Degree of automation
Evaluates the extent to which tickets were supported overall by AI:- L0: No AI, except for identification/categorization
- L1: AI used for text revision
- L2: Adopted the basic agent’s text suggestion
- L3: Confirmed the proposal of a specialist agent
- L4: Dark processing with approval
- L5: Complete dark processing
Agent Overview
The table view lists the AI agents with active automation, in other words, those who process tickets with approval (L4) or fully autonomously (L5). For each of these AI agents, the following are displayed:- Processed: Number of tickets handled in the period
- Waiting for approval: Cases currently pending manual approval
- Automatically processed cases (L4+L5): The total successfully automatically completed tickets
- Dark Processing Rate (L5): Proportion of cases that were closed without human intervention
- Human Approval Rate (L4): Proportion of cases where an employee approved the AI suggestion
- Error rate: The percentage of cases that needed to be corrected or withdrawn