# Understanding trends

Sauce AI is constantly reviewing each piece of new feedback across all sources. Converts them into highlights and automatically clusters anything that is 70% or more similar. We call these thematic similarities — trends. There's a few different types of trends in Sauce. Let's break down the differences between each.&#x20;

<figure><img src="https://3667243797-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fpm0JU36SpVnTviWb6W4x%2Fuploads%2F91Fzf1NNVL6cDUYoRwJY%2FTrends%20Animation.gif?alt=media&#x26;token=6bdffa78-fc45-4e1f-9dfa-2eecc401ce15" alt=""><figcaption></figcaption></figure>

{% tabs %}
{% tab title="Emerging & largest trends" %}
When you log into Sauce, you see a listing of emerging trends. This is the most recent highlights analysed by Sauce, clustered into a trend based on any historical similarities.

<figure><img src="https://3667243797-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fpm0JU36SpVnTviWb6W4x%2Fuploads%2FwFM0AqrFG2lYKpj1dP2Y%2FEmerging%20trends.png?alt=media&#x26;token=6f9c64da-c761-41d6-aa25-96d49b9dac3d" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Generated on-the-fly" %}
Anytime you search, Sauce clusters all feedback into a summarised view of trends so that you can instantly see thematic insights across your search. The same rule applies to `Saved views` and `Saved clusters`. Views and clusters will automatically update as new feedback enters Sauce — enabling you to see new issues as they arise in real time.

<figure><img src="https://3667243797-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fpm0JU36SpVnTviWb6W4x%2Fuploads%2FcI040aqzXi9N1y0Q2SU9%2FGenerated%20on-the-fly.png?alt=media&#x26;token=855cfe40-c773-443b-ae80-738e8bb690c6" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Top down trends" %}
Top-down trends show real-time patterns across **all feedback sources.** Giving you a glanceable, birds-eye-view of what your customers are saying. You can drill-in to any trend to unpack sub-trends. Learn more about [Top-down trends](https://support.sauce.app/tools/top-down-trends).

<figure><img src="https://3667243797-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fpm0JU36SpVnTviWb6W4x%2Fuploads%2FFPUzPg77o5PHOMgd72SQ%2FTop%20down%20trends.png?alt=media&#x26;token=0ab2b20f-b4c1-43a3-a611-36421d89178f" alt=""><figcaption></figcaption></figure>
{% endtab %}
{% endtabs %}

### What's in a trend?

<figure><img src="https://3667243797-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fpm0JU36SpVnTviWb6W4x%2Fuploads%2FoNcBNaOb6JGDExB6U7fd%2FTrend%20drawer.png?alt=media&#x26;token=e830ed3f-5a25-4418-aa61-c09155b5931d" alt=""><figcaption></figcaption></figure>

There's a few things you can do when reviewing a trend:

* Understand which customers are impacted by this trend
* Tracking a trend by saving as a cluster.
* Understand its recent growth and change
* Exporting all highlights
* Add tags


---

# 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://support.sauce.app/fundamentals/understanding-trends.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.
