The Overview dashboard provides a comprehensive view of system-wide performance, error rates, and health status across key components in the Cognigy.AI platform.
View the following visualizations:
Indicators
Active Alerts
The total number of alerts received across your organization.
Errors
The total number of errors received across your organization.
Line Chart
Messages
The total number of user inputs processed per minute. This metric helps track the overall system load.
Panel
Voice Gateway
Voice Gateway metrics are under development and will be available in future releases.
Shows the number of voice inputs processed per minute. This metric helps monitor the volume of voice data being transcribed and processed, providing insights into the activity and load on the Voice Gateway system.
| Subcomponent / Alert Status | 🟢 Inactive | 🔴 Active |
|---|
| SIP Trunk Connectivity | - | - |
| STT (Speech-to-Text) | - | - |
| TTS (Text-to-Speech) | - | - |
Endpoints
Shows the number of requests processed per minute for each Endpoint.
| Subcomponent /Alert Status | 🟢 Inactive | 🔴 Active |
|---|
| Transformer | The number of errors thrown by the Endpoint Transformers is less than 100 in the last 5 minutes. | The number of errors thrown by the Endpoint Transformers is higher than 100 in the last 5 minutes. |
| Realtime Translation | The number of real-time translation errors is less than 100 in the last 5 minutes. | The number of real-time translation errors is higher than 100 in the last 5 minutes. |
Flows
Shows the 90th percentile processing time of Flows in milliseconds, representing the value below which 90% of executions fall. This metric helps identify performance bottlenecks and ensures most Flow executions complete within an acceptable time frame.
| Subcomponent /Alert Status | 🟢 Inactive | 🔴 Critical |
|---|
| NLU | - | - |
| Flow Execution | - | - |
| Extensions | - | - |
| LLM | The number of errors thrown during Large Language Model prompt execution is less than 100 in the last 5 minutes. | The number of errors thrown during Large Language Model prompt execution is higher than 100 in the last 5 minutes. |
| KAI (Knowledge AI) | The number of errors thrown by the knowledge search operations is less than 100 in the last 5 minutes. | The number of errors thrown by the knowledge search operations is higher than 100 in the last 5 minutes. |
Handover Providers
Shows the rate of errors per minute when Cognigy.AI attempts to forward messages from the AI Agent to a handover provider.
| Subcomponent / Alert Status | 🟢 Inactive | 🔴 Critical |
|---|
| Live Agent | - | - |
| 3rd Party Contact Center | - | - |