# AI Classification

The AI classification page serves as a platform for manually adding files as samples to facilitate learning about specific labels. Users can upload files to the AI classification page, providing samples that enable the AI system to better understand and recognize the characteristics associated with particular labels. By adding files manually, users contribute to the training process of the AI model, allowing it to gain insights and improve its accuracy in classifying data according to predefined labels.

<figure><img src="/files/Qoc2n7jHnWfCXj17Xa4P" alt="" width="563"><figcaption><p>AI Classification Page</p></figcaption></figure>

Users can initiate the process by clicking on **upload data** which will redirect them to a separate page dedicated to uploading files for each label. Once redirected, users will have the option to upload files specifically associated with individual labels, facilitating targeted learning and training for the AI system.

<figure><img src="/files/ui030tG83CWkmFXIgiWx" alt="" width="563"><figcaption><p>Adding Files to AI</p></figcaption></figure>

**AI Classification: System Training Options**\
After uploading training files, users can return to the main **AI Classification** page to select one of three training options for the system:

1. **Existing Guard System Files**: Utilize the pre-existing training files already available within the Guard system.
2. **User-Uploaded Files**: Train the system specifically using the files uploaded by the user.
3. **Train All Data**: Combine both the existing system files and the newly uploaded user files for comprehensive training.

<figure><img src="/files/jm64r6UV4vgbacl3Rq29" alt="" width="413"><figcaption><p>Available Data to Train</p></figcaption></figure>

**Prerequisites for Uploading Files**\
To achieve the best results when training the system, please keep the following recommendations in mind:

* **File Quantity**: Upload at least 30 files per label to ensure the system has sufficient data for accurate classification.
* **Data Quality**: The more files you upload, the higher the accuracy of your model will be. Increased file volume allows the AI to better understand and differentiate between labels.
* **Balance**: Try to upload a similar number of files for each label. Balanced data improves the model’s performance and prevents biases during classification.


---

# 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://manual.cybral.com/business/ai-classification.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.