> 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.md).

# What are AI moderated studies?

AI moderated studies are the fastest way to get interview-depth insights at scale. This study type lets an AI moderator conduct conversational sessions with participants on your behalf, dynamically guiding them through your topics, asking for clarification, and probing deeper based on their responses. Want to understand how people think about a concept or experience, but don't have time to run dozens of one-on-one interviews? Try an AI moderated study.

In Dscout, some key AI moderated study features include:

* **An adaptive AI moderator:** Define your research objectives and questions, and the AI moderator leads each session by asking dynamic follow-ups to dig deeper and gather the insights you need. No two sessions are exactly alike, but your research objectives stay consistent.
* **Talk out loud and Task questions:** Combine open-ended **Talk out loud** questions, website or prototype **Task** questions, and closed-ended **Multiple choice** and **Scale** questions in a single session. 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).
* **Continuous recording and transcription:** Each participant's screen, webcam, and audio are recorded and transcribed for the entire session, so you get a full session recording alongside AI-generated summaries and themes.
* **Research at scale, in any language:** Run sessions asynchronously across time zones, and let participants respond in one of 25+ supported languages. Responses 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).

{% hint style="info" %}
**Note:** AI moderated studies are **desktop-only**. Participants must join from a desktop or laptop computer using the Chrome browser—they can't complete a session on a mobile device.
{% endhint %}

### Recruitment options

To find participants for an AI moderated study, you can:

* Add participants from an existing Dscout screener.
* Auto-recruit from Dscout's Scout Panel.
* Auto-recruit from Dscout's Partner Panels.
* Invite your own participants using a share link.
* Add participants from Private Panels.

For more information, see [Recruitment options in an AI moderated study](/ai-moderated-studies/what-are-ai-moderated-studies/recruitment-options-in-an-ai-moderated-study.md).

### AI moderated studies vs. interview studies

{% hint style="success" %}
**Tip:** Already conducted a moderated interview study? You can scale it to hear from even more participants with an AI moderated study. Turn the questions you already asked yourself into an unmoderated study. For more information, see [Scale an interview study with AI moderator](/interview-studies/manage-an-interview-study/scale-an-interview-study-with-ai-moderator.md).
{% endhint %}

AI moderated studies are ideal when you want to:

* Collect interview-depth responses from a large number of participants without scheduling one-on-one sessions.
* Explore concepts, experiences, or attitudes through open-ended conversation at scale.
* Run research asynchronously across time zones and outside business hours.
* Reduce the time and effort of manual moderation while still capturing rich, qualitative data.

However, you might be wondering whether to use an AI moderated study or an interview study. To help, here's a comparison of each study type:

| Capability              | AI moderated study                                     | Interview study                              |
| ----------------------- | ------------------------------------------------------ | -------------------------------------------- |
| **Moderation**          | An AI moderator conducts every session automatically   | A live human moderator runs each session     |
| **Scheduling**          | Participants complete sessions on their own time       | Sessions are individually scheduled          |
| **Question types**      | Talk out loud, Task, Multiple choice, and Scale        | Open-ended conversation with live follow-ups |
| **Follow-up questions** | AI-generated follow-ups based on participant responses | The moderator asks follow-ups in real time   |
| **Session recording**   | Automatic recording and transcription                  | Automatic recording and transcription        |
| **Observers**           | Not applicable                                         | Invite hidden stakeholders to watch live     |
| **Best for**            | Depth at scale                                         | Deep, nuanced one-on-one exploration         |

For more information on interview studies, see [What are interview studies in Dscout?](/interview-studies/what-are-interview-studies-in-dscout.md) Or if neither of these seems to be the right fit, read more about our other study types in the [Dscout quickstart guide](/getting-started/dscout-quickstart-guide.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.md?ask=<question>&goal=<user_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.