> ## Documentation Index
> Fetch the complete documentation index at: https://dev.writer.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Event logs

> View, filter, search, and export request-level logs to debug issues and audit agent activity in AI Studio.

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.

<Info>
  The Events page is only available to organization admins, IT admins, and AI
  Studio full access roles.
</Info>

<Note>
  Event logs are available for [no-code and prebuilt
  agents](/no-code/introduction), [Agent Builder
  agents](/agent-builder/overview), and
  [API](/api-reference/api-keys)/[SDK](/home/sdks) usage. Event logs are not yet
  available for WRITER Agent.
</Note>

## Access the Events page

To open the Events page, [log in to AI Studio](https://app.writer.com/aistudio), select **Billing & reporting** in the left sidebar, then select **Observability**.

<img src="https://mintcdn.com/writer/vFbqizVppcKHxTck/images/observability-logs-events/navbar-dropdown-observability.png?fit=max&auto=format&n=vFbqizVppcKHxTck&q=85&s=68623e93185880074cff87f69c01af1d" alt="The Events page in AI Studio showing summary metrics, a request volume chart, and an events table" width="2996" height="1708" data-path="images/observability-logs-events/navbar-dropdown-observability.png" />

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.

<Note>
  The **Created by** field displays a name only when the completion request is
  sent by an Agent Builder or no-code application. Requests sent through the
  public API display **N/A** for this field.
</Note>

## Export event logs to CSV

Download event data as a CSV file for offline analysis, audits, or sharing with your team. The export reflects the events in the events table for your current view.

To export events, select the download button to the right of the search and filter controls above the events table.

<img src="https://mintcdn.com/writer/vFbqizVppcKHxTck/images/observability-logs-events/events-export-csv.png?fit=max&auto=format&n=vFbqizVppcKHxTck&q=85&s=0ac5d0ffcdcc673ab38dd901726c4eaf" alt="Download button on the Observability page, to the right of the Status and Model filters" width="2985" height="741" data-path="images/observability-logs-events/events-export-csv.png" />

The downloaded file follows these rules:

* **Time range**—the export includes only events within the time range currently selected on the Events page.
* **Masking**—if [content masking](#mask-sensitive-content) is enabled, request and response columns are hidden in the export, matching what you see in the event detail panel.

## 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.

<Note>
  If prompts and responses appear as empty values,
  [masking](#mask-sensitive-content) is enabled.
</Note>

## 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.

<Note>
  Masking also applies to [CSV exports](#export-event-logs-to-csv) and data
  forwarded through [observability plugins](/home/plugins-overview), such as
  [Datadog Logs](/home/plugins/datadog-logs).
</Note>

## Next steps

* [Agent observability](/home/agent-observability): Drill into session logs and performance metrics for individual agents
* [Usage and spend](/home/usage-and-spend): Track organization-wide costs and token consumption
* [Configure plugins](/home/plugins-overview): Stream event data to external platforms like Datadog