# Create a custom collection

## Create a custom collection from scratch

Akto allows you to create a custom collection from scratch using Agentic components from other collections.

In the demonstration below, we have illustrated the steps to help you create a custom collection from scratch.

Go to **Agentic AI Discovery > Agentic Collection**. Click on **Create new collection** to open then dialog and click on **Add Agentic components**. Then you can add Agentic components using different conditions as per your requirement and click on **Create** to save the collection.

{% embed url="<https://demo.arcade.software/aSbt5oRcd8bGgobspJCi?embed=>" %}
Create custom collection from scratch
{% endembed %}

## Create a custom collection from another collection

Akto allows you to create a custom collection directly from other collections.

In the demonstration below, we have illustrated the steps to help you create a custom collection from another collection.

Go to **Agentic AI Discovery > Agentic Collection**. Go to any collection whose Agentic components you want to add in the collection and select those Agentic components. Then click on **Add to Agentic Group** to open the selection dialog box. Choose any Agentic group from there or create a new one as per your requirements.

{% embed url="<https://demo.arcade.software/1pjwS1gRqCyek97X5mJr?embed=>" %}
Create custom collection from another collection
{% endembed %}

**NOTE:** Adding Agentic components to a custom collection creates a reference to the original Agentic components in the custom collection. It does not duplicate them. Thus any changes to the original Agentic components are automatically reflected in the custom collections.


---

# 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://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/agentic-ai-discovery/how-to/how-to-create-a-custom-collection.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.