> 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-chat.md).
# Ursa Chat
Ursa is designed to be conversational. You can type questions, give instructions, and have discussions as you would with a colleague.
## Send a message
1. In the navigation pane, select . The chat window is displayed.
2. Enter your message in the text input area. See [Prompt tips](#prompt-tips).
{% hint style="info" %}
To write a multi-line prompt, press **Shift + Enter** to add a new line without sending the message.
{% endhint %}
3. Press **Enter** to send your message. Ursa provides responses in formatted text that may include the following elements:
* **Bold text** and headings for emphasis and organization
* **Bulleted and numbered lists** for step-by-step instructions
* **Links** to relevant pages or resources within Asset Panda Pro
* **Structured data**, such as tables or formatted field information
***
### Prompt tips
The more specific your prompt, the better Ursa's response.
* **Be specific**: Instead of vague questions, include details like collection names, field names, or specific criteria.
* **Vague:** *Show me assets.*
* **Better:** *Show me all laptops in the IT Assets collection that are assigned to the New York office.*
* **State your needs**: Clearly state whether you want information, a form, an automation, or a filter:
* *Create a form to check out equipment with fields for employee name, department, and expected return date.*
* *Build an automation that sends an email notification when a warranty expires.*
* **Ask follow-up questions**: Ursa remembers your conversation context, so you can build on previous messages without repeating yourself.
* *How many assets are overdue?*
* *Which ones are assigned to the engineering team?*
* *Can you filter the collection to show just those?*
* **Provide examples when helpful**: If you cannot describe what you need, give an example of the result you expect.
* *I want a filter that shows something like: all records where Status is Active and Location is Warehouse A.*
***
## Copy chat text
You can copy chat messages to share with others.
1. Click **Copy** . The chat text is copied and ready to paste elsewhere.
2. To copy the contents of a response table, click **export as csv** above the table and then select the location to save the exported content.
***
## Edit a previous message
You can modify a message you already sent to update the chat response.
1. Find the message you want to edit in the conversation.
2. Click **Edit** :pencil-line: below your message.
3. Modify your text.
4. Press **Enter** to re-send the updated message.
Ursa generates a new response based on your edited message.
***
## Provide feedback
You can provide feedback to help improve Ursa's accuracy and usefulness over time. When you provide feedback, your rating is recorded along with the conversation context.
* :thumbs-up: : The response was helpful and accurate.
* :thumbs-down:: The response was unhelpful or incorrect.
{% hint style="info" %}
Do not hesitate to select that a response was not helpful. Honest feedback is the best way to help Ursa improve.
{% endhint %}
Your feedback is also visible to your organization's administrators in the AI chat logs
---
# 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-chat.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.