> For the complete documentation index, see [llms.txt](https://help.dscout.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.dscout.com/ai-moderated-studies/analyze-an-ai-moderated-study/visual-intelligence.md).

# Visual intelligence

{% hint style="info" %}
*This feature is only available on AI moderated studies and is currently in open beta, which means it is ready for you to use, but there will be changes in functionality leading to a general release. Check back here for the latest updates, and if you have any issues or feedback, our support team is always happy to help at* [*support@dscout.com*](mailto:support@dscout.com)*.*
{% endhint %}

Visual intelligence takes AI moderated studies beyond what participants say, reading their webcam and screen during a session to surface moments of confusion or hesitation, delight or surprise, and more. These moments are then available for analysis alongside participant recordings and transcripts. 

Moments surfaced by visual intelligence fall into two categories:

{% columns %}
{% column %}

#### Expressions

Moments of emotion captured from a participant's webcam:

* **Happiness:** Participant appears settled, comfortable, or at ease.
* **Delight:** Participant expresses a genuine positive reaction.
* **Surprise:** Participant has a realization or encounters something unexpected.
* **Frustration:** Participant appears frustrated or expends effort without progressing.
* **Confusion:** Participant tries and struggles to make sense of something.
  {% endcolumn %}

{% column %}

#### Screen

Moments of navigation or interaction captured from a participant's screen:

* **Hesitation:** Participant considers an action without actually taking one.
* **Looping:** Participant repeatedly returns to the same place without progressing.
* **Friction:** Participant takes an incorrect or unintended action.
* **Direct path:** Participant completes the task requested without difficulty.

{% hint style="info" %}
**Note:** Screen moments are only captured during task questions.
{% endhint %}
{% endcolumn %}
{% endcolumns %}

To use visual intelligence, the feature must first be enabled in your Dscout account by an Account Owner, Admin, or Editor. Then, the setting must be enabled on any question within an AI moderated study where you want to use it. For more information, see the sections below.

### Enable visual intelligence in an account

Before visual intelligence can be used in any study, it needs to be turned on for your account. Expressions and screen data are controlled independently, so your organization can enable one without the other.

{% hint style="info" %}
**Note:** Only Account Owners, Admins, and Editors can access these settings. Turning these settings on for your account does *not* automatically enable them for existing study questions. For more information, see [Enable visual intelligence on study questions](#enable-visual-intelligence-on-study-questions).
{% endhint %}

**To enable visual intelligence for your organization:**

{% stepper %}
{% step %}
Click the name of your account in the left sidebar. Then, click the **Settings (gear)** icon. Your account settings are displayed.

<div align="left"><figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FaOseFXqhAjawrvLRxAb3%2FVisual_intelligence%20(2).jpg?alt=media&amp;token=dc8a7468-c0d9-4904-a7dc-32a99f864a19" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
Open the **AI** tab. Then, set the **Expressions** and/or **Screen** toggles to **ON**.

<div align="left"><figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FsBGNBiXaWP3umqpm2A6G%2FVisual_intelligence.jpg?alt=media&amp;token=9dc695f5-d044-458f-985d-4253655b1aca" alt=""><figcaption></figcaption></figure></div>
{% endstep %}
{% endstepper %}

Now, visual intelligence is enabled for your Dscout account, and users building studies can turn the feature on within those studies. To disable visual intelligence for your account, follow the steps above and set the respective toggles to **OFF**.

### Enable visual intelligence on study questions

Once visual intelligence is enabled in your Dscout account, individual users can use the feature on study questions in AI moderated studies. The setting is off by default for all question types.

{% hint style="info" %}
**Note:** Visual intelligence and [Privacy blur](/study-basics/testing-prototypes/privacy-blur.md) can't be enabled at the same time on a single task question because privacy blur intentionally hides a participant's screen. Turn off privacy blur first if you want to enable visual intelligence on that question, or vice versa.
{% endhint %}

**To enable visual intelligence on a question:**

{% stepper %}
{% step %}
On the **AI moderator** tab of your study, click a question to edit it.
{% endstep %}

{% step %}
Under Question settings, set the **Visual intelligence** toggle to ON.

<div align="left"><figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FwAYcdo8lJGnKaKAEgsph%2FVisual_intelligence%20(9).jpg?alt=media&amp;token=5fdd62fa-efa9-460c-afd4-4f61d455baa4" alt=""><figcaption></figcaption></figure></div>
{% endstep %}
{% endstepper %}

Now, visual intelligence is enabled for that question. You'll see a chip on the question indicating visual intelligence is on:

<figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2Ff3QfKp3UtXSIokpe89nA%2FVisual_intelligence%20(1).jpg?alt=media&amp;token=7fcdc9e7-ada9-4290-a8fd-a928d857ef96" alt=""><figcaption></figcaption></figure>

To disable visual intelligence on a question, repeat the steps above and set the toggle to **OFF**.

### Analyze visual intelligence data

Once your study starts collecting responses, visual intelligence moments appear in three places: each participant's full session recording view, beside individual responses on the **Questions** view, and as tags across your responses.

#### Full session recording view

Open a participant's session in the full session recording view, then select the **Visual intelligence** tab in the right sidebar. Every moment found in that session is listed in chronological order, alongside markers on the scrub bar. Use the **All** / **Expressions** / **Screen** filter to narrow the list to one category, and click any moment to jump straight to that point in the recording:

<figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FW7h69grAY0TovYY8CDll%2FVisual_intelligence%20(8).jpg?alt=media&amp;token=553f3075-c1a9-4a4a-9a7f-960d680b218c" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
**Note:** You can also add, edit, or delete moments by hand from this tab if Dscout AI missed something or flagged something you'd rather remove.
{% endhint %}

#### Questions view

For each response to a question with visual intelligence enabled, any moments it surfaced are displayed alongside the standard summarized response for that participant. Here, you can click the **Play** icon to go directly to that moment in the participant's session recording:

<figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FZPm6US3yjzo5TzUUobrn%2FVisual_intelligence%20(5).jpg?alt=media&amp;token=0c5eaa05-a975-4427-b5f7-e4a1a2da6d56" alt=""><figcaption></figcaption></figure>

#### Tags

Every moment visual intelligence identifies is also saved as a tag in your study, letting you browse and filter moments across all responses the same way you would any other on the **Tags** view.

* **Happiness**, **Delight**, **Surprise**, **Frustration**, and **Confusion** each get their own tag group.
* All four Screen signals (**Hesitation**, **Looping**, **Friction**, and **Direct path**) share a single **Screen** tag group.

<figure><img src="https://3976082747-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIKfn7RcT4CW9XaIbqAdd%2Fuploads%2FDUBA8hhySJupyrAefV6x%2FVisual_intelligence%20(3).jpg?alt=media&amp;token=a1b28e2a-2c2f-4c0e-aced-fb563f3526df" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
**Note:** These tag groups are generated automatically and can't be renamed or deleted.
{% endhint %}


---

# 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://help.dscout.com/ai-moderated-studies/analyze-an-ai-moderated-study/visual-intelligence.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.