# Product Recommendation Engines
## Overview
You can send out product recommendations in your customer emails based on the opt-in preferences indicated by the customer.
Promotional content such as product recommendations should only be sent to users that have opted-in to receive such communications. You will have to provide us with this information.
{% hint style="warning" %}
Product recommendations in emails *must* be customer-specific. parcelLab is *not* responsible for the content of the emails and does *not* assume any guarantee.
{% endhint %}
## Configuring Product Recommendation Engines
The following sections describe the configuration required for including product recommendation engines in email communication.
{% hint style="info" %}
You can also include product recommendations using the space.vars.Product\_Campaigns functionality and display recommended products in emails, on your space.vars.Product\_OrderStatus, and in the space.vars.Product\_ReturnsPortal with parcelLab’s product recommendation engine. For further information, see [how to configure parcelLab product recommendations](https://docs.parcellab.com/docs/engage/campaigns/parcellab-product-recommendations).
{% endhint %}
### Customer Requirements
To integrate promotional content from product recommendation engines in email communication, you need to provide the following general information:
* The list of all users that have opted-in to receive product recommendations and the corresponding recipient data, including the email address.
* The product recommendation engine that you want to use.
* In which emails to display the promotional content (for example: order delivered emails).
### Product Recommendation Engine Requirements
The following sections describe the information required to implement specific product recommendation engines.
#### Emarsys Predict
Product recommendations from Emarsys use Predict, which can be included into the relevant email templates by parcelLab.
To integrate links to product recommendations from Emarsys in email communication, you need to provide the following information to parcelLab:
* Set up a recurring .csv export to our server on the Emarsys platform in order for us to get the product data.
* Your Merchant ID and ID of the widget.
* A daily export file with the predictUserID and predictSecret of all customers.
{% hint style="info" %}
You can download export files from your Emarsys account that contain the predictUserID and predictSecret, as well as the name and email address of the customer. It is also important to get the opt-in/opt-out information for customers.
{% endhint %}
* A HTML code snippet so it can be integrated in email templates.
The HTML is shown, which can be easily integrated into messages/templates.
```
```
{% hint style="info" %}
For more information about the Emarsys Predict product recommendation engine, refer to the [Emarsys official documentation](https://help.emarsys.com/hc/en-us/articles/115003942913-Predict-Email-Recommender-Overview).
{% endhint %}
#### Nosto
To integrate links to product recommendations from Nosto in email communication, you need to provide a HTML code snippet so it can be integrated in email templates by parcelLab.
The type of recommendation and how it looks in the messages is completely set up in Nosto's platform. The HTML code snippet is generated based on the chosen parameters and this code is included in our templates.
{% hint style="info" %}
For more information about the Nosto product recommendation engine, refer to the [Nosto official documentation](https://help.nosto.com/en/articles/634622-getting-started-with-email-personalization-widgets#copy-and-visual-settings).
{% endhint %}
### Other Supported Product Recommendation Engines
The following product recommendation engines are also supported:
* Certona
* Dynamic Yield
{% hint style="info" %}
For more information on the scope and requirements for implementing these product recommendation engines, please contact your parcelLab representative.
{% endhint %}
### Implementation Process
When parcelLab has the required information, the setup process can begin for the selected product recommendation engine. The recommendations are added to emails in the form of a link, which when added into the template of emails displays the recommendations.
For example:
\\
\
---
# 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.parcellab.com/docs/engage/messages-and-journeys/overview/product-recommendations.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.
