# Test Drive Scenario

1. Log into Microsoft Fabric: Go to[ app.fabric.microsoft.com](https://app.fabric.microsoft.com/)
2. [Add a Lakehouse and create the destination table](https://learn.microsoft.com/en-us/fabric/data-engineering/create-lakehouse).
   1. Below is a sample Lakehouse table schema for the scenario.  The SQL script is run in a notebook, which will generate your table.  Note that there are various methods for creating a schema.

```
%%sql
CREATE TABLE Sales_Orders_Sample (
Customer_Name STRING,
Company STRING,
Order_Date DATE,
Order_No STRING,
Part_Classification STRING,
Part_Name STRING,
Qty INT,
Price STRING,
Address STRING,
City STRING,
State STRING,
ZipCode STRING,
Phone STRING,
Notes STRING
) USING DELTA;
```

2. [Upload your Source data file(s) to the Lakehouse](https://fabricdocs.osmos.io/adding-data-into-a-lakehouse)
   1. Below are two sample files to run through your Wrangler.

{% file src="/files/FWinuDKWGH1nhCeLrWTa" %}

{% file src="/files/PT6LCqI5YZXRowt8QRts" %}

3. [Create an AI Data Wrangler](https://fabricdocs.osmos.io/ai-data-wrangler/create-an-ai-data-wrangler)
4. [Provide Instructions](/ai-data-agents-on-microsoft-fabric/ai-data-wrangler/instructions.md)
   1. Below are sample instructions

{% tabs %}
{% tab title="Manual Instructions" %}

1. If the Order Date field is blank, set the date to 01/01/1900
2. Remove $ from the Price.
3. Extract or Infer City, State, and Zip Code from Address
4. Phone number should be in (XXX) XXX-XXXX US Phone number format. You can skip the country code
5. Part Classification can only take one of these two values.  Figure out how to map any values in the source to one of these five values.

   Product

   Service
   {% endtab %}

{% tab title="Descriptor Instruction" %}
Start Order No with *PLU.*
{% endtab %}
{% endtabs %}

3. [Run Your Wrangler](https://fabricdocs.osmos.io/ai-data-wrangler/running-a-wrangler)
4. [Write the data to your Destination](https://fabricdocs.osmos.io/ai-data-wrangler/writing-to-the-destination)


---

# 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://agenticdocs.osmos.io/ai-data-agents-on-microsoft-fabric/ai-data-wrangler/test-drive-scenario.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.