# Overview

**AI Studio** is an all-in-one platform that enables you to build, fine-tune, test, and deploy AI models efficiently and at scale.\
It provides a unified environment that simplifies the AI development lifecycle — from data preparation to production deployment — without requiring deep infrastructure management.

### **Why AI Studio**

Developing and deploying large language models (LLMs) and machine learning models often involves fragmented tools, manual configuration, and complex infrastructure setup.\
AI Studio eliminates these challenges by offering an integrated workflow that combines **data management**, **model training**, **evaluation**, and **serving** into one seamless experience.

With AI Studio, you can:

* Fine-tune pretrained foundation models with your own datasets.
* Manage models, datasets, and experiments through a centralized interface.
* Deploy models instantly for inference or testing.
* Scale your compute resources on demand.
* Monitor performance and optimize costs through built-in analytics.

### **Key Features**

| Feature               | Description                                                                                                          |
| --------------------- | -------------------------------------------------------------------------------------------------------------------- |
| **Data Hub**          | Manage, upload, and version datasets with secure storage and access control.                                         |
| **Model Fine-tuning** | Customize foundation models using your own data with automatic resource management and distributed training support. |
| **Model Hub**         | Centralized repository for storing, versioning, and deploying models for inference.                                  |
| **Model Testing**     | Evaluate model quality and compare performance across model versions.                                                |
| **User Token**        | Secure API authentication and user-based permission management.                                                      |

### **Who Can Use AI Studio**

AI Studio is designed for:

* **Data Scientists** who need to fine-tune and evaluate custom models.
* **Developers** who want to integrate AI into applications through APIs.
* **Researchers** who experiment with large-scale model training.
* **Businesses** that require scalable AI infrastructure without managing servers or GPUs directly.

### **Core Benefits**

* **Unified Workflow:** One platform for all AI lifecycle stages — from data to deployment.
* **Scalability:** Automatically scales compute and storage resources for large workloads.
* **Ease of Use:** Intuitive interface and SDKs for both technical and non-technical users.
* **Traceability:** Every dataset, model, and job is versioned for reproducibility.
* **Cost Efficiency:** Pay only for what you use, with transparent billing and resource optimization tools.

### **AI Studio Modules Overview**

AI Studio is built around modular services that work seamlessly together:

1. **Data Hub** – Prepare and manage datasets.
2. **Model Fine-tuning** – Train and optimize pretrained models.
3. **Model Testing** – Validate and benchmark model performance.
4. **Model Hub** – Store, manage, and deploy models.
5. **User Token** – Authenticate and control access to all services.

Each module can be used independently or as part of an end-to-end workflow — empowering you to move from prototype to production faster.

### **Next Steps**

To get started:

1. Review the **Before You Start** section to understand the platform architecture and prerequisites.
2. Follow the **Quickstart** guide to fine-tune and deploy your first model.


---

# 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-docs.fptcloud.com/fpt-ai-studio/before-you-start/overview.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.