> 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/built-in-ai-features/refine-your-questions.md).
# Refine your questions
| Study type | Availability |
|---|
| Screeners | true |
| Usability tests | true |
| Media surveys | true |
| Intercept studies | true |
To collect useful data, you have to ask the right questions. And sometimes what makes sense to you as an expert might not be entirely clear to your participants. Dscout AI can help by offering suggestions on screener and study questions. Write your questions as you normally would, then get feedback from Dscout AI on how to make them clearer right in the builder.
**To refine your questions with Dscout AI:**
{% stepper %}
{% step %}
In your screener or study, add questions on the **Screener**, **Usability test**, **Media survey**, or **Mission** tabs.
{% endstep %}
{% step %}
Click the **Refine your questions** icon in the top right corner of the builder.
{% endstep %}
{% step %}
Click **Get suggestions**.
{% endstep %}
{% endstepper %}
Now, Dscout AI assesses the questions across your study for clarity, concision, and more. If a question needs more context, you’ll see that in your suggestions. If a question will be easier to analyze when split in two, you’ll see that as well.
Access your generated suggestions at any time by clicking the **Refine your questions** icon.
Here, you have the following options for each suggestion:
* **Accept & replace:** Implement the suggestion(s) into your study. Your existing question will be replaced with the suggestion provided in the modal. This cannot be undone, so review the suggestions carefully.
**Note:** You may receive multiple suggestions for a single question. Be sure to review all suggestions before accepting.
* **Reject:** Dismiss the suggestion from the modal. You can regenerate rejected suggestions by clicking the **Get new suggestions** button. For more information, see [Refresh suggestions](#h_01K6BHABSTV9GJ2GJM4GY8DB6B).
* **Copy suggestion:** Copies the suggestion to your clipboard. You can then manually paste the suggestion into a new question in your study.
If you want to implement all suggestions provided by Dscout AI, you can click **Accept all** at the bottom of the modal to replace all of your questions with the updated versions.
{% hint style="info" %}
**Tip:** You’ll also find suggestions directly on questions in the builder. After generating, questions will show a suggestion icon. Click the icon to view Dscout AI’s suggested edits.
{% endhint %}
## Refresh suggestions
If you make edits to your research, you can get new suggestions from Dscout AI.
**To refresh suggestions:**
{% stepper %}
{% step %}
Click the **Refine your questions** icon in the top right corner of your screener or study.
{% endstep %}
{% step %}
Click the **Get new suggestions** button at the bottom of the modal.
{% endstep %}
{% endstepper %}
Now, Dscout AI reassesses your questions and provides new suggestions. Use the actions listed above to incorporate or dismiss any suggested edits.
## What suggestions will I get?
As with all generative AI tools, it’s important to keep in mind what Dscout AI is looking for when providing suggestions. This can help clarify any advice that may seem at odds with your research goals.
To provide suggestions, Dscout AI looks for:
* **Definitions and context:** Dscout AI will suggest defining terms it believes participants may be unfamiliar with. As long as a term is defined somewhere in your study, it shouldn’t suggest defining it again.
* **Clarity:** Dscout AI will suggest simplifying language that it believes may be confusing for participants.
* **Double-barreled questions (typed response and talk out loud questions only):** Dscout AI will suggest splitting double-barreled questions (questions that ask participants multiple questions in one).
{% hint style="info" %}
**Tip:** Dscout AI’s suggestions are just that—suggestions. Maybe you specifically wrote a question to be double-barreled. You won’t hurt Dscout AI’s feelings by rejecting its suggestion to split it.
{% endhint %}
To learn more about how Dscout AI can help speed up your research, see [What is Dscout AI?](/dscout-ai/what-is-dscout-ai.md).
For information on how Dscout works to keep your data safe when building AI features, see [AI privacy and security in Dscout](/dscout-ai/what-is-dscout-ai/ai-privacy-and-security-in-dscout.md).
---
# 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/built-in-ai-features/refine-your-questions.md?ask=&goal=
```
`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.