# Architecture

**AIGI Network architectual framwork**

<figure><img src="/files/drjWOh40oDNNqJ84sh9o" alt=""><figcaption></figcaption></figure>

**Connection Layer**\
After users connect to the AIGI network, they contribute their idle internet bandwidth to the network. By adopting our Tentacle Procedure, the network specifically routes and crawls datasets related to the crypto field, storing them in the initial data layer.

**Initial Data Layer**\
This layer stores data of varying granularity in a unified database, ensuring unparalleled scalability and availability.

**Specialized Data Layer/Other Data Layers**\
The specialized data layer stores all crypto-related data collected, while other data layers store non-crypto data. Our data orchestrator, composed of AI tools and validators, directs the organization of data in the initial data layer to isolate the specialized data needed, ensuring that the data is clean and valid.

**AIGI Model Layer**\
The AIGI model layer consists of the AIGI framework, AIGImate（now AIGIClaw）, and AIGITrading. It uses the large volume of crypto-specific data from the specialized data layer to pre-train our AI models. Additionally, user interactions with AIGImate（now AIGIClaw） and AIGITrading feed data that further refines these models to meet user needs.

**Application Layer**\
To enhance model performance, we fine-tune our AI systems based on real-world user needs, continuously improving precision and efficiency. New datasets generated through user interactions with AI applications are fed back into the AIGI model layer for iterative training and refinement.


---

# 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://aigi-protocol.gitbook.io/aigi-protocol/overview/user-facing/aigi-network/architecture.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.