> For the complete documentation index, see [llms.txt](https://prohelp.assetpanda.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://prohelp.assetpanda.com/ursa/ursa-administrator-tasks.md).
# Ursa Administrator tasks
## Enable or disable UrsaAI
Administrators control whether Ursa is available to users in the organization.
1. In the navigation pane, select 
**Settings** > **Preferences**.
2. Select the **Ursa****AI** toggle. Ursa is enabled for all users in your organization. Users can select  **Ursa** to use the assistant to answer questions, build workflows, and find assets.
3. To disable Ursa, deselect the **Ursa****AI** toggle. The Ursa interface is no longer accessible to users.
{% hint style="info" %}
If Ursa is disabled, the existing conversation history and logs are preserved and are made available if you re-enable the assistant.
{% endhint %}
***
## View Ursa chat logs
Administrators can review all Ursa conversations that occur within the organization. This is useful for monitoring usage, reviewing response quality, and ensuring Ursa is used appropriately. This can help you identify common questions that could be addressed through better account configuration, training materials, or documentation.
Each log entry contains the following information:
* **Session details**: Date, time, and duration of the conversation
* **User information**: User who initiated the conversation
* **User messages**: User prompts and questions
* **Ursa responses**: Full text of Ursa's replies
* **Feedback ratings**: Thumbs up or thumbs down feedback provided by the user.
1. In the navigation pane, select  **Tools** > **Activity stream**.
2. Select **AI Logs**.
3. To locate logs that contain specific keywords, enter the search term in the **Search** field.
4. To filter the log based on specified criteria, click :filter:. See [Filter the Activity Stream](/tools/activity-stream.md).
5. To view the details of a conversation, click **View details** in the conversation row.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://prohelp.assetpanda.com/ursa/ursa-administrator-tasks.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.