Explorer¶

After the application is created successfully, the system aggregates each Agent / LLM request as a log event in the Explorer. You can search, filter, and analyze all Session and Trace data for a single application or all applications.

The top of the page supports switching between Agent and LLM status, with Agent status as the default.

Agent Status¶

In Agent status, two filter boxes are displayed at the top of the page:

Agent Type: Filter by all Agent types or a specific type;
Instance: Filter by specific instances under the selected Agent type, with support for searching instance names. After selecting a specific Agent type, the instance filter only shows instances under that type. When no Agent type is selected, the instance filter defaults to all instances but is not selectable.

LLM Status¶

Switch to LLM status, and the top of the page displays an application filter control, allowing you to select all applications or a specific LLM application for viewing.

View Modes¶

User List¶

The Agent global Explorer supports aggregating data across Agent types by User dimension. The detail page of a single Agent type also provides a User tab for viewing User usage under that type.

The Agent type detail page contains the following top-level tabs:

Instance List / User List / Session / Trace

Session List¶

Session dimension data is displayed by default. The list fields include Session ID, Input Tokens, Output Tokens, Risk Event Count, and Alert Level. The left-side quick filter supports filtering by token range, model provider, request model, response model, and other dimensions. Multiple analysis views are supported, including list, top list, time series, pie chart, treemap, and grouped table.

Risk Event Count: The total number of risk events detected in the current Session;
Alert Level: The highest alert level among risk events in the current Session. If there are no risk events, it shows a no-risk status.

Click a row to enter the Session detail page:

Overview: The left side displays the Session Trace waterfall chart, while the right side shows preview, attribute information, and the alert level of the current Session;
Call Analysis: Displays the call ratio of models, Tool executions, and Skill executions, as well as the Trace and risk events associated with the current Session. Risk events show the alert level, related operations, and occurrence time.

Trace List¶

Switch to the Trace List tab to view data by Trace dimension. The list fields include Trace ID, Associated Session, Trace Duration, Input Tokens, Output Tokens, Trace Status, Risk Operation Count, and Alert Level.

Risk Operation Count: The number of operations marked as risky in the current Trace;
Alert Level: The highest alert level among all risk operations in the current Trace.

Click a row to enter the Trace detail page:

Overview: Displays the Trace call process using a waterfall chart, along with the alert level of the current Trace. Span details are shown below;
Call Analysis: Displays Tool and Skill call records. Risky operations show a risk indicator, and the risk level is also displayed in the related Tool, Skill, and other operation information.

Detail Page¶

When you enter the detail page, the left side displays a single Span and Trace generated by the application, while the right side shows the corresponding preview and attribute information.

Risk Alert¶

The system marks risks on objects such as Sessions, Traces, Tools, and Skills based on risk events generated during Agent execution.

Risk alert information may appear in the following locations:

Location	Display Content
Session List	Risk Event Count, Alert Level
Session Overview	Alert level of the current Session
Session Call Analysis	Risk events and associated Traces
Trace List	Risk Operation Count, Alert Level
Trace Overview	Alert level of the current Trace
Trace Details	Risk operation indicator, and risk levels of operations such as Tool and Skill

When a Session or Trace contains multiple risk events, the list and overview display the highest alert level. You can click a specific risk event or risky operation in the call analysis to jump to Security Monitoring for details.

Related Operations¶

Search by node name source;
Choose whether to display metrics and scores.

What are metrics and scores?

Metrics: duration time display
Scores: Model quality evaluation scores, descriptions, etc.

Preview¶

Includes node type, node name, execution duration, token consumption, execution status, and execution details.

Status Display¶

Execution Status (`status`)	Possible Causes
Success: Success
Failure: Error	Agent / LLM call timeout, tool returns exception, etc.
Warning: Warning	Output content triggers sensitive word detection but execution is not interrupted, etc.

Execution Details¶

Displays the Input and Output of the application. The Input contains all elements used to build the final request to the model, while the Output shows the result generated based on the input.

Attribute Information¶

Related field information for the current Span or Trace.

Associated Views¶

Using the + button in the top-right corner, you can bind built-in views to the current detail page to display Agent / LLM data in a dedicated manner.

Click the Add button;
Select the associated field;
In the Bind Built-in View panel that appears, select the view to associate;
After binding is successful, the new tab will be displayed in the tab bar.