Skip to main content
The Events page in AI Studio captures every LLM request across your organization, giving you a searchable, filterable log of all platform activity. Use it to debug failed requests, audit model usage, and understand how your agents interact with LLMs.
The Events page is only available to organization admins, IT admins, and AI Studio full access roles.
Event logs are available for no-code and prebuilt agents, Agent Builder agents, and API/SDK usage. Event logs are not yet available for WRITER Agent.

​
Access the Events page

To open the Events page, log in to AI Studio and select Events from the left sidebar. The Events page in AI Studio showing summary metrics, a request volume chart, and an events table Use the time range controls to select a preset window or define a custom start and end time. The summary metrics, chart, and events table all update to reflect the selected range.

​
Find specific events

The events table lists every request with its timestamp, HTTP status code, model, session ID, who created it, and latency. To narrow the table to the events you need, use any combination of the following:
  • Filters—narrow by status (success or failure), model, or the user that created the request. Combine filters to isolate specific scenarios, such as all failed requests for a particular model.
  • Search—search by exact request ID or session ID to locate a specific event.
  • Time range—adjust the time window to focus on a specific period of activity.

​
Inspect an event

Select any row in the events table to open the detail panel. The panel has three tabs:
  • Details—session and request IDs, timestamp, latency, status, request type, cache hit status, token usage and cost, model and provider, and runtime (start time, end time, duration).
  • Request—the full JSON request payload.
  • Response—the full JSON response payload.
Use the Request and Response tabs together to debug unexpected model behavior, and the Details tab to understand cost, performance, and routing for any individual request.
If prompts and responses appear as empty values, masking is enabled.

​
Mask sensitive content

Event logs can capture sensitive information from user prompts and LLM responses. To protect this data, content masking hides these fields in the event detail panel, where they appear as empty values. Masking is enabled by default. To configure masking, select the Configure masking control on the Events page. Choose one of the following options and select Confirm:
  • Enable masking—user prompts and LLM responses are hidden. These fields appear as empty values in event logs.
  • Disable masking—user prompts and LLM responses are fully visible in event logs.
Masking also applies to data forwarded through observability plugins, such as Datadog Logs.

​
Next steps