# Screenshots

In [Hotkeys / Triggers](/inbox-ai/hotkeys-triggers.md), you can set a hotkey to capture a part of your screen and send it to your AI action for processing. Let's dive into the default screenshot processor and see how it works. It goes beyond the scope of this documentation to fully explain all the possibilities, rather we will explain the basics.

After you finish the [Quick Start](/inbox-ai/quick-start.md), you should be ready to try out your hotkey. In [Hotkeys / Triggers](/inbox-ai/hotkeys-triggers.md) you can see which action will be run when you tap the hotkey.

<figure><img src="/files/izddgqOs4bkfISFVeFzR" alt=""><figcaption><p>By default, the Extract Tasks &#x26; Add action will add an Apple Reminder</p></figcaption></figure>

Under [Advanced Settings](/inbox-ai/advanced-settings.md) you can configure more. For instance, you can specify whether the screenshot itself is sent to the AI, or if Inbox AI should try to extract the text itself using an on-device image-to-text processor and just send that. Sending the screenshot required a vision-capable AI model, and takes more effort and time, but often yields better results.

<figure><img src="/files/kSR0x0tkm21IClUb3fF6" alt=""><figcaption></figcaption></figure>

When you tap the hotkey, draw a rectangle around the text you want to capture, and when done, the image (or text from the image) will be sent to the selected action. By default this is the "Extract Tasks & Add (Apple Reminders)" action, but you can change this as you please.

<figure><img src="/files/ZWCa0ktb6PMJRfunEmN5" alt=""><figcaption><p>Use the hotkey and drag a rectangle around the text you want to use as input for the AI</p></figcaption></figure>

After this, a notification will pop up, and your reminder will appear in Apple Reminders.

To customize the behavior, you can select a pre-built example or fully build your own AI actions. Let's look at the current default. Go to "Actions", and open the "Apple Reminders" folder in the sidebar, and select "Extract Tasks & Add" below it.

<figure><img src="/files/OQlPipRXe2RACaosBInw" alt=""><figcaption></figcaption></figure>

This is an [Ask AI](/inbox-ai/actions/custom-actions/ask-ai.md) action, which uses the default AI provider. The prompt defines its behavior and it gives the AI access to two follow-up actions:

* Add Apple Reminder
* Send Notification

In the prompt, you can specify the behavior you are looking for. The `{{ value }}` placeholders in the prompt will be replaced by variables before sending them to the AI. In this case the `{{ originalInput | process }}` is the extracted text from the screenshot (the image itself is also attached if you enabled that option). You can also see some time information being added, as the AI does not know what time it currently is. For more information on templating, see the [Templating](/inbox-ai/templating.md) page.

In this case the AI can choose the run the built-in "Add Apple Reminder" action, but if you explore the other examples, you can customize this to nearly anything on your Mac or on the Web.


---

# Agent Instructions: 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:

```
GET https://dreetje-1.gitbook.io/inbox-ai/screenshots.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.