For the complete documentation index, see llms.txt. This page is also available as Markdown.

Explore your data

Study type
Availability

Usability tests

Media surveys

Intercept studies

AI moderated studies

Interview studies

Diary studies

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:

1

Navigate to the Responses tab of your study.

2

Click the Explore your data icon in the left sidebar.

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.

You can start a new thread with Dscout AI by refreshing the page or navigating away then back to explore your data.

Define chat context

When exploring your data with Dscout AI, you’re in total control. That means you can tell it exactly which questions or sessions to reference when responding to your prompts.

Each question or session from your study is listed in the left sidebar. All are selected by default at the start of your chat, but you can select or deselect any here to have Dscout AI only focus on those.

You can specify questions or sessions in your prompts to Dscout AI. However, any questions or sessions you reference must also be selected in the left sidebar.

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 See more beneath the response from Dscout AI:

That response’s sources are displayed in a modal. Click a source to go straight to that response. Take note of the question number provided for each source. This will help you locate the applicable question in the participant’s response.

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

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.

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

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:

Understanding qualitative data

  • What are some themes in responses about feature X?

  • Summarize participant feedback on the onboarding process collected in Question 3.

Finding specific information

  • Show me 3–5 quotes that mention usability issues.

  • What did participants say about the checkout experience?

Generating insights

  • What are some of the pain points users experienced?

  • What suggestions did participants offer in Question 8 for improving the feature?

Exploring sentiment

  • How did participants feel about the new interface?

  • What aspects of the product received positive feedback?

May struggle with

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

Segment comparison

  • How do responses vary based on age? Compare 18–24 yr olds to 25–30 yr olds.

  • How do feelings towards this feature differ between paid and unpaid subscribers?

Auto-filtering or study modification

  • Find me video responses from frequent users.

  • Tag all responses that mentioned X with “X” tag.

Quantification or quantitative analysis

  • How many participants experienced X issue with the feature?

  • What was the average amount of time spent on task #2?

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.

For information on how Dscout works to keep your data safe when building AI features, see AI privacy and security in Dscout.