> 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/create-an-ai-moderated-study/add-questions-to-an-ai-moderated-study.md). # Add questions to an AI moderated study AI moderated studies combine open-ended and closed-ended questions to conduct dynamic, engaging sessions for each participant. For added control, you can set how many follow-up questions the moderator should ask, as well as define any guidance on what exactly those follow-ups should be designed to discover. AI moderated studies always have study questions, and they also include screener questions if you're auto-recruiting participants. {% hint style="success" %} **Tip:** For the full list of available question types, see [Question types in AI moderated studies](/ai-moderated-studies/what-are-ai-moderated-studies/question-types-in-ai-moderated-studies.md). {% endhint %} ### Screener questions (auto-recruit only) When auto-recruiting, screener questions use knockout logic to qualify or disqualify applicants before they interact with the AI moderator. Only **Multiple choice** questions are supported in the screener. {% hint style="info" %} **Note:** In addition to screener questions, you'll want to include targeting attributes to narrow your audience further. For more information, see [Targeting attributes](/recruit-participants/dscout-scout-panel/targeting-attributes.md). {% endhint %} **To add a screener question:** {% stepper %} {% step %} Navigate to the **Screener** tab of your study.

{% endstep %} {% step %} Click **+ Add** under **Screener questions** in the left sidebar. {% endstep %} {% step %} Select **Multiple choice** to add a new multiple choice question.

{% endstep %} {% step %} Enter a **Prompt** and your answer **Choices**. {% endstep %} {% step %} Configure knockout logic using the drop-down beside each choice. For more information, see [Knockout questions](/recruit-participants/dscout-scout-panel/knockout-questions.md).

{% hint style="success" %} **Tip:** You can also select **Add from question bank** to add a saved question from your question bank. For more information, see [Question banks](/study-basics/question-types/question-settings-and-organization/question-banks.md). {% endhint %} {% endstep %} {% step %} Click **Done**. {% endstep %} {% endstepper %} Now, your screener question is added to your study. Repeat the steps above to add more screener questions (up to 10 total) or move on to adding your study questions. ### Study questions Study questions are the heart of your AI moderated study. This is where the AI moderator takes over, leading a conversation based on your objectives, prompts, and follow-up guidance. When auto-recruiting, only applicants who qualify on your screener questions advance to your study questions. {% hint style="success" %} **Tip:** Once you've added your study questions and configured their settings, you can have Dscout AI give everything a quick pass and offer suggestions on what could lead to a more successful study. For more information, see [Review your study](/dscout-ai/built-in-ai-features/review-your-study.md). {% endhint %} **To add study questions to your AI moderated study:** {% stepper %} {% step %} Navigate to the **AI moderator** tab of your study.

{% endstep %} {% step %} Click **+ Add** in the center of the builder or under **Questions** in the left sidebar. {% endstep %} {% step %} Select a question type and complete the provided fields.

{% hint style="success" %} **Tip:** For more information on individual question settings, search for its question type on the Dscout help center. {% endhint %} {% endstep %} {% step %} Click **Done**. {% endstep %} {% endstepper %} AI moderated studies support a maximum of **5 Task questions** and **30 questions total** (excluding Multiple choice and Scale questions). Your study's estimated length is displayed at the top of the builder and updates as you add questions. We recommend keeping studies to 30 minutes or less to avoid participant fatigue. ### Follow-up questions You're in control of how dynamic or rigid you want the AI moderator to be when interacting with your participants. For example, maybe you want the AI moderator to dig a little deeper on certain questions but not on others. You can customize the number of follow-up questions the AI moderator asks on a question-by-question basis. To enable follow-ups on a study question, set the **Follow-up questions** toggle in the right sidebar to **ON**, then choose from the following options:

* **Only if response is short:** Up to one follow-up, but none if the participant's initial response is already thorough. * **1 follow-up:** One follow-up, regardless of how thorough the initial response is. * **2–3 follow-ups:** At least two follow-ups (no more than three total), regardless of how thorough the initial response is. You can also guide the kinds of follow-ups the moderator asks. For example, focusing on competitors a participant mentions, or asking the reasoning behind a closed-ended selection. Enter that in the **Follow-up guidance (optional)** field:

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://help.dscout.com/ai-moderated-studies/create-an-ai-moderated-study/add-questions-to-an-ai-moderated-study.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.