# Technical Architecture

### Data Pipeline

* Wallet Connection → WalletConnect, MetaMask, Trustwallet or other Web3 wallets
* Multi-Chain Data Collection → Etherscan, Arbiscan, BscScan APIs (later on Polygonscan, etc.)
* AI Analysis Engine → GPT-4o mini processes wallet vectors
* Persona Classification → 6 core types with confidence score
* Dashboard UI → History, persona, insights

### Technical Architecture

* Frontend: Next.js + Tailwind CSS + shadcn/ui
* Backend: NestJS + Node.js microservices
* Database: MongoDB Atlas (persistent) + Redis cache
* Blockchain Data Layer: Etherscan, BscScan, Polygonscan APIs
* AI/ML: GPT-4o mini (Free) + Claude Sonnet (Pro)
* Deployment: Vercel (frontend) + Railway (backend)

####

### Technology Highlights 🔧

#### AI Technology

* GPT-powered AI engine (GPT-4o mini for MVP, Claude Sonnet for Pro)
* Behavioral pattern recognition
* Wallet activity clustering and analysis

#### Performance

* \~60 seconds for a full persona report
* Optimized caching for repeated analyses

#### Analysis Metrics

* Transaction frequency & size
* Token holdings & distribution
* NFT holdings & trading activity


---

# 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://cryptosona.gitbook.io/cryptosona-docs/technical-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.