# Customer Data

The Customer Table contains details of your Customers. This table has two mandatory fields: `customer_id` (string) and `customer_since` (date). You can also add additional data present in your Customer records, which can help improve accuracy of your Models.

{% hint style="warning" %}
The `customer_id` field is the primary key of this table. Each data record must have a Unique value for this field.
{% endhint %}

<table><thead><tr><th width="187">Field Name</th><th width="118">Data Type</th><th width="124">Example</th><th>Description</th></tr></thead><tbody><tr><td>*customer_id</td><td>String</td><td>e131498</td><td>This is the key field, used for Identification of Customers. All values in this field must be Unique.</td></tr><tr><td>*customer_since</td><td>Date</td><td>2010-12-21</td><td>Date of first contact with the Customer. This field is vital for future predictions, and every customer should have a value for this field.</td></tr><tr><td>customer_gender</td><td>String</td><td>female<br>Ms.<br>LLC</td><td>Gender or Title of the Customer; Used as Categories for Pattern Recognition.</td></tr><tr><td>customer_age</td><td>Date</td><td>1997-06-22</td><td>Date of birth of Customer / Date of foundation of Customer company. Missing values are acceptable.</td></tr><tr><td>zipcode</td><td>String</td><td>50676</td><td>ZipCode of the Customer.</td></tr><tr><td>customer_country</td><td>String</td><td><p>France</p><p>DE</p></td><td>Country where the Customer is based; Used as Categories for Pattern Recognition.</td></tr><tr><td>email_ending</td><td>String</td><td>gmail.com<br>live.com</td><td>Customer's email address provider. If email is mapped to this field, the part before @ is automatically removed; Used as Categories for Pattern Recognition</td></tr><tr><td>phone</td><td>String</td><td>0176<br>0153</td><td>The starting digits of the Customer's phone number; Used as Categories for Pattern Recognition</td></tr></tbody></table>


---

# 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://documentation.crossengage.io/predictions-platform/data-model/customer-data.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.