> 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/draft-a-study-with-dscout-ai.md).
# Draft a study with Dscout AI
Dscout AI can help you draft entire screeners and studies, chatting through research goals, defining recruitment criteria, and writing comprehensive study questions. Unsure where to start when testing your Figma prototype? Have an idea of what you want to learn but no concrete plan on how to get answers? Dscout AI can take you from question to launch-ready in no time.
**Dscout AI can help you draft the following:**
* Standalone screeners.
* Usability tests.
* Media surveys.
* AI moderated studies.
{% hint style="info" %}
**Note:** To draft a study with Dscout AI, you must first have a project set up in Dscout. For more information, see [Create a project, mission, or screener](/getting-started/workspaces-and-projects/create-a-project-mission-or-screener.md).
{% endhint %}
**To draft a study with Dscout AI:**
{% stepper %}
{% step %}
Click the **Draft with Dscout AI** button in the top right corner of your project. A new chat with Dscout AI is displayed.
{% endstep %}
{% step %}
Enter and send a prompt (or choose a starter prompt) to begin chatting with Dscout AI.
{% hint style="success" %}
**Tip:** It is not possible to upload a document into a chat with Dscout AI. Instead, we recommend copying the content from any research briefs or other documents and pasting them in the chat directly.
{% endhint %}
{% endstep %}
{% step %}
Continue chatting with Dscout AI to confirm some study basics, including:
* Research objectives.
* Recruitment approach and criteria.
* Prototype or website URLs you wish to test.
{% hint style="success" %}
**Tip:** If you're testing a password-protected Figma prototype, be sure to provide the password in the chat with Dscout AI. Dscout AI will then help you work it into your study so participants can access it.
{% endhint %}
{% endstep %}
{% endstepper %}
Once Dscout AI has enough information, your chat will narrow to the left of the page and a draft will open on the right. You can continue chatting with Dscout AI to make adjustments, or you can edit question and answer text directly:
{% hint style="info" %}
**Note:** Studies drafted with Dscout AI won’t include skip logic or multivariate questions. You can add these manually in the builder. For more information, see [Open a drafted study in the builder](#h_01KM67TFN8FRZPEFSC006S5C45).
{% endhint %}
When everything looks good, refer to the next section to learn how to move into the builder where you’ll launch your screener or study.
## Open a drafted study in the builder
When you and Dscout AI have gotten your study to a good place, you’ll open your study in the builder. Here, you can give everything one final look and adjust advanced settings like skip logic and randomization before opening your study to participants.
**To open your study in the builder:**
{% stepper %}
{% step %}
Click **Create mission** in the top right corner of the Dscout AI chat window. A modal is displayed containing your study’s details.
{% endstep %}
{% step %}
Verify the following details are correct, as populated by your chat with Dscout AI.
{% hint style="info" %}
**Note:** The fields displayed in this modal will vary based on screener or study type.
{% endhint %}
{% endstep %}
{% step %}
Click **Create mission**.
{% endstep %}
{% endstepper %}
Now, your study opens in the builder. Here, you can adjust advanced settings like skip logic and randomization, verify your study overview and incentive, and launch your study when everything looks exactly how you want it.
## View chat history
Previous chats with Dscout AI are available even after they’ve been turned into launched studies. Existing chats can serve as good starting points if you need to conduct similar research. Pick up right where you left off, chat with Dscout AI to make any needed changes, then launch your next study.
{% hint style="info" %}
**Note:** You only have access to your own previous chats, and the chat history is project-specific. You’ll only see chats from the project through which you access Dscout AI.
{% endhint %}
**To view your Dscout AI chat history:**
{% stepper %}
{% step %}
Click the **Draft with Dscout AI** button in the top right corner of your project. A new chat with Dscout AI is displayed.
{% endstep %}
{% step %}
Click the **History (clock)** icon in the left sidebar.
{% endstep %}
{% endstepper %}
Now, a list of your previous chats is displayed. Click any chat to open it again right where you left off:
## Start a new thread with Dscout AI
While you’re drafting with Dscout AI, you can start a new thread at any time to work on something new. Previous threads are available in your chat history, so you can switch back to your existing conversation when you’re ready.
**To start a new thread with Dscout AI,** click the **New thread (plus)** icon in the left sidebar:
Now, a new chat opens where you can talk through new ideas, share new research objectives, and draft a new study.
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).
---
# 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/draft-a-study-with-dscout-ai.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.