Event dashboard, monitor logs and user management
Events dashboard
The events dashboard displays all configured monitoring events in a tabular format:
Entity name: The agent or application being monitored
Entity type: Classification (App, Agent, Playground, etc.)
Input: The query/input being evaluated
Output: The response being assessed
Run frequency: How often does evaluation occur
Last run: When the last evaluation occurred
Last status: Current status with the ‘Configure’ option
Use the search box and dropdown filters, Entity (All/App/Agent/Prompt/Reasoning) and Status (All, Success, Failed, Error), to quickly locate specific events. Click ‘Configure’ in the ‘Last Status’ column to modify event settings. You can also check the running status for agent events that have been triggered (e.g., by a cron job) but have not yet posted logs from the ‘Last Status’ column, which provides real-time visibility into execution progress before results are finalized.
Bulk delete for monitor logs
You can delete multiple event logs at once from the Monitor Events screen.
Use the checkboxes next to each event name to select the ones you want to remove.
After selecting the desired events, click the ‘Delete’ button located at the top-right corner of the screen.
Monitor logs
The monitor logs interface provides detailed performance tracking:
Key components
Event information header
Event ID: Unique identifier for the monitoring event
Entity name: The app/agent being monitored
Entity type: Classification (App, Agent, Playground, etc.)
Frequency: How often monitoring occurs
Metric: Performance criteria being measured
Log status visualization
Colored bars provide a quick visual indicator of recent execution results
Red bars indicate failures, green indicates successful evaluations
Filtering options
Status dropdown: Filter by All/Success/Failed/Error status
Log time dropdown: Filter by active/inactive
Log details table
Log ID: Unique identifier for each log entry
Log time: When the evaluation occurred
LLM response: The query or prompt content
Credits: Resource utilization
Cost: Associated expense
Metrics: Success (✅), Failure (❌)
Status: Outcome (Success/Failed/Error with color coding)
Monitor Logs give you clear, instant visibility into every evaluation run:
Dual-format scores – Each metric displays both the raw value and its percentage (for example, 1.1 (21%)), so you never have to convert figures manually.
Automatic model metadata – The evaluation engine chooses GPT-4o when required and records the model name, token usage, and system instructions for every event.
Built-in diagnostic notes—Metrics that require interpretation, such as Health Check, include read-only notes that explain the scoring logic.
View a detailed log
Click any Log ID in the Monitor dashboard.
The right-hand panel opens, showing the full metric breakdown, model metadata, and diagnostic notes for that execution.
Troubleshooting
Investigate failed evaluations by reviewing the specific LLM responses
Check metric scores to understand why responses did not meet thresholds
Adjust prompts or application or agent configuration based on monitoring insights
User management in monitor
Monitor supports role-based user permissions. Admins can assign access to specific users who can view and configure monitoring events.
How to manage users
From the Monitor page, select any monitoring event.
Navigate to the ‘User Management’ tab.
A user management panel opens with the following elements:
Entity name: Name of the agent/app.
Entity type: AGENT or APP
Builder: Select the builder you want to invite. The options include custom or everyone.
When selecting the ‘Custom’ option, you can use the search field to locate builders to invite. Enter the user’s name and click the ‘Invite’ button to assign them the Builder role.
When selecting the 'Everyone' option, all users will get access to the Monitor module.
Once accepted, the user will see the Monitor tab upon login and will be able to manage the assigned event.
Last updated