> 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/what-are-ai-moderated-studies/ai-moderated-study-faq.md).
# AI moderated study FAQ
Below, you'll find answers to some of the most common questions about AI moderated studies.
### General
What is an AI moderated study?
An AI moderated study lets an AI moderator conduct conversational, interview-style sessions with your participants. Using your research objectives and questions as a guide, the AI moderator asks questions, seeks clarification, and probes deeper based on each participant's responses so you get interview-depth insights at the speed and scale of an unmoderated study.
How much control do I have over what the AI moderator asks?
You set the direction with your research objectives and questions, and the AI moderator follows it, asking dynamic follow-ups to probe deeper. You can also control which questions offer follow-ups, including specific guidance on what follow-ups to ask. For more information, see [Add questions to an AI moderated study](/ai-moderated-studies/create-an-ai-moderated-study/add-questions-to-an-ai-moderated-study.md).
Can the AI moderator see the participant's screen during a task?
No. During a Task question, the AI moderator bases its questions only on the participant's spoken or written responses—not on any action taken on their screen. The screen is still recorded for you to review during analysis.
Does the AI moderator take into account data from my other studies during a session?
No. Each session is self-contained—the AI moderator is guided only by that study's research objectives and questions, and by what the participant says during the session. If you want it to account for earlier research, write that context into your study's objectives or moderator context.
Can I run sessions in languages other than English?
Yes. You can run your study in more than 25 supported languages. When enabled, participants choose their preferred language at the start of their session from your chosen list, and responses and transcripts are translated back to English for analysis. For more information, see [Manage language of an AI moderated study](/ai-moderated-studies/create-an-ai-moderated-study/manage-language-of-an-ai-moderated-study.md).
### Building a study
What question types can I use?
You can combine **Talk out loud** (open-ended), **Task** (website or prototype), **Multiple choice**, and **Scale** questions. For more information, see [Question types in AI moderated studies](/ai-moderated-studies/what-are-ai-moderated-studies/question-types-in-ai-moderated-studies.md).
Will the AI moderator automatically ask "why" after a closed-ended question?
If you want the reasoning behind a closed-ended (Multiple choice or Scale) answer, enable follow-up questions on that question (with specific follow-up guidance) or add an explicit follow-up in the form of another question. For more information, see [Question types in AI moderated studies](/ai-moderated-studies/what-are-ai-moderated-studies/question-types-in-ai-moderated-studies.md).
How long should a session be?
We recommend keeping AI moderated studies to 30 minutes or less to avoid participant fatigue. Your study's estimated length is displayed at the top of the builder and updates as you add questions.
Can I edit my study after it's launched?
No. You can't edit an AI moderated study once it's been launched, so we recommend testing your study first. For more information, see [Test an AI moderated study](/ai-moderated-studies/create-an-ai-moderated-study/test-an-ai-moderated-study.md).
### Participants and the session experience
What is a participant told at the start of an AI moderated session?
The AI moderator introduces itself as Dscout AI and sets expectations for the session, including that it's AI-led, roughly how long it will take, and that the entire session will be recorded. If you want to add a custom greeting, you can do so. For more information, see [Manage participant experience in an AI moderated study](/ai-moderated-studies/create-an-ai-moderated-study/manage-participant-experience-in-an-ai-moderated-study.md).
How are participants told they're interacting with AI?
It's disclosed in a few places: AI moderated studies carry an "AI conversation" label in the Dscout participant app, and the study's details page states that participants will converse with an AI moderator.
Can participants complete a session on their phone?
No. AI moderated studies are desktop-only. Participants must join from a desktop or laptop computer using the Chrome browser.
## Recording and privacy
What's recorded during a session?
Each participant's screen, webcam, and audio are recorded and transcribed for the entire session. You'll get a full session recording alongside AI-generated summaries and themes.
Do participants still complete screen-share setup even if I don't require screen sharing?
Yes. All AI moderated sessions require participants to share their screen, so every participant completes screen-share setup before they begin.
## Analysis
How are responses analyzed?
Alongside each full session recording and transcript, Dscout AI generates summaries and themes for open-ended questions and surfaces emerging themes across participants. For more information, see [View AI moderated study responses](/ai-moderated-studies/analyze-an-ai-moderated-study/view-ai-moderated-study-responses.md).
How is my data organized when the AI asks each participant different follow-ups?
Even though each participant may get different follow-ups, every session is anchored to your original questions and objectives, giving you a consistent structure for comparison.
Each participant's full conversation is captured as its own session, and you can synthesize across them with AI summaries, themes, and full transcripts. For more information, see [View AI moderated study responses](/ai-moderated-studies/analyze-an-ai-moderated-study/view-ai-moderated-study-responses.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 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/what-are-ai-moderated-studies/ai-moderated-study-faq.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.