# Aizen Platform Interfaces

This diagram shows the interfaces to the Aizen platform.

<figure><img src="/files/G371vmklxNvtv2O2Xri4" alt=""><figcaption><p>Aizen Platform Interfaces</p></figcaption></figure>

There are three interfaces into the Aizen platform.

## Data Sources

This interface connects your database and streaming data sources to the Aizen platform. Databases are connected as JDBC endpoints. Stream sources are connected as Kafka endpoints. There are methods to connect CSV files, Snowflake, and Cloud data sources as well.

## Prediction Request Sources

This interface connects your prediction application to the Aizen platform. Prediction applications make REST requests to an http endpoint in the Aizen platform. There are mechanisms to connect batch sources such as databases and Cloud data sources for batch predictions, as well as Kafka endpoints for predictions on streaming data.

## Job Management

You manage machine learning jobs via a Jupyter notebook connection to the Aizen platform. You may run jobs to create ML features from your data, train an ML model or deploy a trained ML model for prediction.


---

# 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://aizen-corp.gitbook.io/docs/introduction/aizen-platform-interfaces.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.