> For the complete documentation index, see [llms.txt](https://docs.mdintegrations.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mdintegrations.com/partner/exploring-features/carepair.md).

# CarePair

CarePair is MDI's product-recommendation engine. It pairs complementary Offerings together so that when a physician prescribes one, they can recommend a related product to the patient in the same conversation — turning a single Encounter into a natural cross-sell opportunity, without the physician ever having to leave the messaging thread to make it happen.

## How it works

CarePair runs on e-commerce metadata you attach to your Offerings catalog. As you build out an Offering, you can add:

* A product **image**
* A **store description**
* A **store URL** (where the patient checks out)
* Other e-commerce-style metadata

When a physician prescribes an Offering that has a CarePair association, they see the paired product(s) surfaced right there in the prescribing flow. Nothing is pushed to the patient automatically — the physician chooses whether to recommend it. If they do, the recommendation goes out as part of a message from the doctor, appearing in the same conversation as the prescription itself rather than as some separate, unattached promotion.

## What the patient sees

What the patient actually sees depends on which messaging experience your Encounters run through.

{% tabs %}
{% tab title="MDI white-label messaging" %}
If your patients use MDI's white-label patient messaging experience (the white-label Patient App or embedded messaging), CarePair recommendations render natively: the patient sees the product card — image, description, and a link — inline in the doctor's message. Tapping it takes them to your store's product page (the store URL you configured) to check out.
{% endtab %}

{% tab title="Custom messaging UI" %}
{% hint style="warning" %}
If you've built your own custom messaging UI instead of using MDI's white-label Patient App, CarePair recommendations will **not** appear automatically. Product recommendations are delivered as `product_recommendations` metadata on the message object — your UI must read that field and render it yourself. Partners on a custom messaging stack who skip this step will have working CarePair pairings on the backend, but their patients will never actually see the recommendations.
{% endhint %}
{% endtab %}
{% endtabs %}

## Recipe: setting up a CarePair pairing

{% hint style="info" %}
Once two or more Offerings carry this metadata, MDI can associate them as complementary pairs — for example, a weight-loss medication paired with a supplement, or a dermatology treatment paired with a skincare product you also sell.
{% endhint %}

{% stepper %}
{% step %}
In the Partner Portal, open the Offering you want to pair and add its e-commerce metadata — image, store description, store URL.
{% endstep %}

{% step %}
Repeat for the complementary Offering.
{% endstep %}

{% step %}
Configure the association between the two Offerings so MDI knows they're a CarePair pair.
{% endstep %}

{% step %}
When a physician next prescribes either Offering, the paired product appears as a recommendation option in the prescribing flow.
{% endstep %}

{% step %}
If using a custom messaging UI, confirm your client reads `product_recommendations` off the message payload and renders it before relying on this in production.
{% endstep %}
{% endstepper %}


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.mdintegrations.com/partner/exploring-features/carepair.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.