> 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/dscout-ai/dscout-ai-studio/explore-your-data.md).

# Explore your data

With Dscout AI, you can get a jump start on analysis by exploring your data in an unstructured, interactive chat. Ask questions about your data, define the specific context, and let Dscout AI find the answers. Then, use the data and sources provided by Dscout AI to dive deeper into participant responses.

Chats reset after eight hours and Dscout AI prioritizes your most recent interactions. You may need to provide additional context when referring to messages further back in the chat history.

### Access explore your data

Select your study type below to learn how to explore your data with Dscout AI:

{% hint style="success" %}
**Tip:** Try clicking the **Explore** button beside AI themes and charts in usability tests, media surveys, and AI moderated studies to bring that data directly into a chat as context.
{% endhint %}

{% tabs %}
{% tab title="Usability tests" %}
**To explore your data in a usability test:**

{% stepper %}
{% step %}
Navigate to the **Responses** tab of your study.
{% endstep %}

{% step %}
Click the **Explore your data** icon in the left sidebar.

![](/files/bf949af8c21a84aaa66bdcaed6c216c19295c0d6)
{% endstep %}
{% endstepper %}

Now, a chat window is displayed. Want to quickly identify pain points in a user flow? Need a handful of quotes that support a new marketing strategy? Just enter your question and let Dscout AI do the rest.

<figure><img src="/files/qG0CuaufspUIQl8u2V7X" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Media surveys" %}
**To explore your data in a media survey:**

{% stepper %}
{% step %}
Navigate to the **Responses** tab of your study.
{% endstep %}

{% step %}
Click the **Explore your data** icon in the left sidebar.

![](/files/bf949af8c21a84aaa66bdcaed6c216c19295c0d6)
{% endstep %}
{% endstepper %}

Now, a chat window is displayed. Want to quickly identify pain points in a user flow? Need a handful of quotes that support a new marketing strategy? Just enter your question and let Dscout AI do the rest.

<figure><img src="/files/qG0CuaufspUIQl8u2V7X" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Intercept studies" %}
**To explore your data in an intercept study:**

{% stepper %}
{% step %}
Navigate to the **Responses** tab of your study.
{% endstep %}

{% step %}
Click the **Explore your data** icon in the left sidebar.

![](/files/bf949af8c21a84aaa66bdcaed6c216c19295c0d6)
{% endstep %}
{% endstepper %}

Now, a chat window is displayed. Want to quickly identify pain points in a user flow? Need a handful of quotes that support a new marketing strategy? Just enter your question and let Dscout AI do the rest.

<figure><img src="/files/qG0CuaufspUIQl8u2V7X" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="AI moderated studies" %}
**To explore your data in an AI moderated study:**

{% stepper %}
{% step %}
Navigate to the **Responses** tab of your study.
{% endstep %}

{% step %}
Click the **Explore your data** icon in the left sidebar.

![](/files/bf949af8c21a84aaa66bdcaed6c216c19295c0d6)
{% endstep %}
{% endstepper %}

Now, a chat window is displayed. Want to quickly identify pain points in a user flow? Need a handful of quotes that support a new marketing strategy? Just enter your question and let Dscout AI do the rest.

<figure><img src="/files/qG0CuaufspUIQl8u2V7X" alt=""><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Interview studies" %}
**To explore your data in an interview study:**

{% stepper %}
{% step %}
Navigate to the **Sessions** tab of your study.
{% endstep %}

{% step %}
Click the **Explore your data** button in the bottom-right corner.

![](/files/cedeffcff24a94733287b926ace9f01741c3b0e4)
{% endstep %}
{% endstepper %}

Now, a chat window opens in a new tab. Want to quickly identify pain points in a user flow? Need a handful of quotes that support a new marketing strategy? Just enter your question and let Dscout AI do the rest.

<figure><img src="/files/oTMXaK0rPrOrwwjF9EtK" alt=""><figcaption></figcaption></figure>
{% endtab %}
{% endtabs %}

### Define chat context

When exploring your data with Dscout AI, you can guide it to certain questions or responses in your prompts. Here are some example prompts:

* In **Q5**, which prototype did participants prefer?
* In the interview sessions with **participant A, participant B, participant C,** what were their biggest concerns or hesitations?

### Review response sources

When Dscout AI provides a response, it will cite its sources so you can take a closer look at where the data came from. Sources lead directly to individual participant responses or sessions so you can see the larger context.

**To review response sources**, click a source from beneath the response or click **See more**:

<figure><img src="/files/lTh7d7ResbTxDsi9dUqi" alt=""><figcaption></figcaption></figure>

That response’s sources are displayed in a modal. Click a source to go straight to that response.

**Or,** click a participant’s name to go to their session:

<figure><img src="/files/FwBbTPZkjB5ov5niWL8H" alt=""><figcaption></figcaption></figure>

### Rate chat responses

To help improve the quality of Dscout AI’s responses, you can rate every response it provides to you. If a response was good, give it a thumbs up. If a response was bad, give it a thumbs down.

<figure><img src="/files/aUYl31jvCPtAoUl21Pkz" alt=""><figcaption></figcaption></figure>

Submitting your feedback will help us continuously improve Dscout AI across all of Dscout, not just when exploring your data.

### View chat history

Analysis can send you in many directions, so it can sometimes be helpful to revisit previous chat threads. Pick up where you left off, ask further questions, and continue analysis you already started.

{% hint style="info" %}
**Note:** You only have access to your own previous chats, and the chat history is study-specific. You’ll only see chats from the study through which you access Dscout AI.
{% endhint %}

**To view your chat history,** click the **History (clock)** icon in the left sidebar:

<figure><img src="/files/sXiYP3G8wQtHrFozIhlY" alt=""><figcaption></figcaption></figure>

Now, a list of your previous chats is displayed. Click any chat to open it again right where you left off:

<figure><img src="/files/yqTdhzvdpQJPNB4fBn9V" alt=""><figcaption></figcaption></figure>

### Start a new thread

If you want to explore a new idea within your data, you can start a new thread. This leaves your existing thread in its current state.

**To start a new thread,** click the **New thread (plus)** icon in the left sidebar:

<figure><img src="/files/STyn8fYUeD2A4uqqENEN" alt=""><figcaption></figcaption></figure>

Now, a new chat opens where you can talk through new ideas and explore your data from the beginning.

### What can I ask?

When using Dscout AI, it’s important to keep in mind the general strengths and weaknesses of any generative AI tool. We’ve put together a list of things Dscout AI excels at as well as a list of some things that might be best saved for manual analysis to help guide your interactions.

#### Excels at

Dscout AI is great for the following types of requests:

| Category                           | Examples                                                                                                                                                              |
| ---------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Understanding qualitative data** | <p></p><ul><li>What are some themes in responses about feature X?</li><li>Summarize participant feedback on the onboarding process collected in Question 3.</li></ul> |
| **Finding specific information**   | <p></p><ul><li>Show me 3–5 quotes that mention usability issues.</li><li>What did participants say about the checkout experience?</li></ul>                           |
| **Generating insights**            | <p></p><ul><li>What are some of the pain points users experienced?</li><li>What suggestions did participants offer in Question 8 for improving the feature?</li></ul> |
| **Exploring sentiment**            | <p></p><ul><li>How did participants feel about the new interface?</li><li>What aspects of the product received positive feedback?</li></ul>                           |

### May struggle with

Dscout AI may have difficulty with the following types of requests:

| Category                                               | Examples                                                                                                                                                                                      |
| ------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Segment comparison**                                 | <p></p><ul><li>How do responses vary based on age? Compare 18–24 yr olds to 25–30 yr olds.</li><li>How do feelings towards this feature differ between paid and unpaid subscribers?</li></ul> |
| **Auto-filtering or study modification**               | <p></p><ul><li>Find me video responses from frequent users.</li><li>Tag all responses that mentioned X with “X” tag.</li></ul>                                                                |
| **Quantification or quantitative analysis**            | <p></p><ul><li>How many participants experienced X issue with the feature?</li><li>What was the average amount of time spent on task #2?</li></ul>                                            |
| **Analysis with studies that were edited post-launch** | Changing a study post-launch affects how data is stored, which can lead to unreliable AI responses.                                                                                           |

To learn more about how Dscout AI can help speed up your research, see [Dscout AI](https://help.dscout.com/hc/en-us/articles/27341160440468).

For information on how Dscout works to keep your data safe when building AI features, see [AI privacy and security in Dscout](https://help.dscout.com/hc/en-us/articles/36270310945428).


---

# 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/dscout-ai/dscout-ai-studio/explore-your-data.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.