# Getting Data Using AI

There are several ways Arcwise AI can be used to retrieve data. Below are some example prompts as well as instructions for saving it to the sheet.

## Example Prompts

> Get me a table of all transactions last year

This prompt can be executed from a blank sheet and will recover a table of transactions from your data warehouse, or other connected data source. This could be **millions of rows** but you will still be able to save it to the sheet and work with the data, both with normal spreadsheet tools and with AI: [Working With Large Data](/using-arcwise-in-sheets/working-with-large-data.md).

> Get me a list of our stores, the total sales at those stores last year, and the YoY change in sales 

This prompt can be executed from a blank sheet and will recover a table of transactions from your data warehouse, or other connected data source. It can also be executed after manually connecting the correct data source: [Connecting Data](/connecting-data/connecting-data.md). This data is likely to be small.

{% hint style="warning" %}
If Arcwise is connected to your data warehouse then you can retrieve tables from an empty sheet. If Arcwise is not connected to your data warehouse, or your administrator has not given the AI access to the data warehouse then you must add tables using the traditional flows: [Connecting data](/connecting-data/connecting-data.md).
{% endhint %}

## Saving Data to the Sheet

After asking the AI analyst for data you can save it to the sheet with the **Save** button.

<figure><img src="/files/bcbzXGHoevuaFQNfsaAk" alt="" width="375"><figcaption></figcaption></figure>


---

# Agent Instructions: 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://docs.arcwise.app/using-arcwise-ai-analyst/getting-data-using-ai.md?ask=<question>
```

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.