> 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/ai-themes.md).
# AI themes
| Study type | Availability |
|---|
| Usability tests | true |
| Media surveys | true |
| Intercept studies | true |
| Diary studies | true |
Dscout AI can identify themes across responses. Think of themes like categories used to group responses together or as tags that highlight commonalities. When initiated, Dscout AI compiles a list of up to 20 themes based on participant responses and automatically applies them where applicable for easy filtering.
## Usability tests, media surveys, and intercept studies
In usability tests, media surveys, and intercept studies, themes are generated on the study level. This means they will be generated for every applicable question at once. And once generated, the results will be available for all collaborators viewing the same study.
{% hint style="info" %}
**Note:** Themes can only be generated once per study. We recommend waiting until your study has 15 or more responses before generating themes, but you can do so with as few as five responses.
{% endhint %}
**To generate AI themes:**
{% stepper %}
{% step %}
Navigate to the **Responses** tab of your study.
{% endstep %}
{% step %}
Click the **AI settings** button in the top-right corner.
{% endstep %}
{% step %}
Click **Start AI analysis**.
{% endstep %}
{% endstepper %}
Generating themes typically takes a few minutes, but it can take a few hours if you have a high number of responses. When your results are ready, you’ll find them on the **Responses** tab:
{% hint style="info" %}
**Note:** If a single prompt asks more than one question, each question is given its own themes. You'll see a drop-down under AI themes during analysis. Make a selection from the drop-down to see its associated AI themes.
{% endhint %}
Once generated, you can show or hide themes from view by returning to the AI settings menu.
## Diary studies
In diary studies, themes are generated on the activity level. This means you can select specific activities to generate results for. Once generated, the results will be available for all collaborators viewing the same activity.
{% hint style="info" %}
**Note:** Themes can only be generated once per activity. We recommend waiting until your activity has 15 or more responses before generating themes, but you can do so with as few as five responses.
{% endhint %}
**To generate AI themes in a diary study:**
{% stepper %}
{% step %}
Navigate to the **Analyze** tab of your study.
{% endstep %}
{% step %}
Click the **AI settings** button in the top right corner.
{% endstep %}
{% step %}
Select activities to analyze.
{% endstep %}
{% step %}
Click **Start AI analysis**.
{% endstep %}
{% endstepper %}
Generating themes typically takes a few minutes, but it can take a few hours if you have a high number of responses. When your results are ready, you’ll find themes for open-ended, screen recording, and video questions on the **Entries** tab:
{% hint style="info" %}
**Note:** If a single prompt asks more than one question, each question is given its own themes. You'll see a drop-down under AI themes during analysis. Make a selection from the drop-down to see its associated AI themes.
{% endhint %}
## Edit themes
Once generated, responses are automatically tagged with the relevant themes. However, you can remove a theme from a response by clicking the **X** beside it:
You can also rename a theme by hovering over it and clicking the pencil icon. Then, enter a new **Theme title**.
Once generated, you can show or hide themes from view by returning to the AI settings menu.
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/ai-themes.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.