> For the complete documentation index, see [llms.txt](https://docs.intelligems.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.intelligems.io/post-purchase-experiences/getting-started-with-post-purchase-upsells/post-purchase-experience-use-cases/recs-vs.-picks.md).

# Recs vs. Picks

Post-purchase offers can pull products two ways. **Shopify recommendations** uses Shopify's Recommendations API, which reads your order history, product descriptions, and collection relationships, then picks per shopper. **Specific products**, **Products from collection**, and **Products with tag** let you decide instead.

Recommendations scale without maintenance and improve as your order history grows. A hand-picked list gives you control over margin and inventory. Which one earns more per order is worth answering rather than guessing.

*What this test design might look like:*

|                    | **Control**             | **Variant A**                 |
| ------------------ | ----------------------- | ----------------------------- |
| **Products shown** | Shopify recommendations | Three hand-picked accessories |

{% hint style="info" %}
Recommendations need order history to work well. On a newer store, or in a category where your catalog doesn't cluster cleanly, a curated list usually starts stronger.
{% endhint %}

Both options are set in the **THEN SHOW** half of your order rules, covered in [How to Set Up a Post-Purchase Upsell Experience](/post-purchase-experiences/getting-started-with-post-purchase-upsells/how-to-set-up-a-post-purchase-upsell-personalization-or-test.md). You can also mix them, using recommendations as your catch-all rule and a specific list for orders that contain a particular collection or tag.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.intelligems.io/post-purchase-experiences/getting-started-with-post-purchase-upsells/post-purchase-experience-use-cases/recs-vs.-picks.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.