> For the complete documentation index, see [llms.txt](https://prismnetwork.gitbook.io/prismnetwork-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://prismnetwork.gitbook.io/prismnetwork-docs/4.-technical-architecture/4.1-architecture-overview-layered-design-and-modular-coordination.md).
# 4.1 Architecture Overview: Layered Design and Modular Coordination
Prism Network adopts a five-layer architecture:
**(1) Account Layer**
Responsible for user onboarding, account management, permission control, and subscription management.
**Engineering Features:**
* Supports major wallet connections (MetaMask, OKX Wallet, TokenPocket, etc.)
* Provides SDK support for Python / TypeScript interfaces
* Account status queries (assets, subscriptions, order history)
* Permission management (per-trade limits, total position caps, execution cycles)
* Supports EIP-712 typed signatures or equivalent human-readable signature formats
**(2) Strategy Layer / Flux**
The technical core of Prism Network. This layer is responsible for converting signals into executable strategy instructions.
**Core Mechanisms:**
* Signal Understanding Module: Synthesizes multi-source signals to output event understanding, probability judgments, and opportunity identification
* Task Decomposition Module: Decomposes complex tasks into subtasks including event matching, price comparison, liquidity checks, rule validation, and risk assessment
* Risk Validation Module: Verifies account authorization, position limits, liquidity conditions, market status, and risk rules
* Strategy Generation Module: Outputs strategy proposals containing event, market source, trade direction, order size, and risk boundaries
**Strategy Library and Experience Learning:**
* Through continuous feedback, the system progressively builds a strategy library and experience repository
* The strategy library codifies approaches for different event types, market structures, and risk environments
* The experience repository records relationships between historical signals and outcomes, helping the system improve judgment efficiency in subsequent similar events
**(3) Execution Layer**
Responsible for converting strategy instructions into actual trades.
**Order Routing:**
Selects the optimal execution venue based on price, depth, slippage, and fees
Supports both order book markets and AMM markets
Splits orders across platforms
**Execution Monitoring:**
Continuously monitors order status, filled prices, and partial fills
Monitors market halts, price deviations, and settlement progress
**Exception Handling:**
Order timeout → Retry or cancel
Excessive price deviation → Re-quote or terminate
Insufficient liquidity → Split order adjustment or delay execution
RPC anomaly → Switch node or pause
Authorization expiration → Notify user or terminate
**(4) Data & Signal Layer**
Responsible for ingesting and processing all external data.
Data Collection: Collects multi-source data via APIs, WebSockets, and on-chain nodes
Data Cleaning: Deduplication, timestamp alignment, anomaly filtering, entity recognition, event mapping
Signal Generation: Event intensity, sentiment direction, fund flow, confidence assessment
Data Output: Structured signals, anomaly labels, source weights, signal confidence scores
**(5) Protocol Layer / Prism**
The underlying settlement and governance system of Prism Network.
**Core Functions:**
* Strategy Account Standard: Data formats, interface specifications, and behavioral standards for Flux
* Settlement Rules: Profit calculation, fee distribution, settlement cycles
* Node Collaboration Mechanism: Node identity, task allocation, incentive rules
* Governance Rules: Token voting, proposal processes, parameter adjustments
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## 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, and the optional `goal` query parameter:
```
GET https://prismnetwork.gitbook.io/prismnetwork-docs/4.-technical-architecture/4.1-architecture-overview-layered-design-and-modular-coordination.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.