# Introduction

## What is Goshen network

Goshen network is an Optimistic rollup protocol to scale transaction throughput with lower gas cost while maintaining decentralization and security from Ethereum - the underlying main chain. The protocol uses a RISC-V machine to support on chain computing and in the event of challenges, it’s only necessary to identify "one step" in the RISC-V-Chain program to execute prune fraud state.

Goshen Network ensures simplicity and versatility with a layered architecture. At the bottom layer is a general-purpose computing environment for the L2, based on RISC-V, migrating L1 computations off-chain in a trustless manner. With this, L2 implements L1’s state transition logic, ensuring full compatibility with the L1 ecosystem. A reliable cross-layer message communication mechanism is further constructed to provide interoperability between L1 and L2 for building upper-layer applications such as a token bridge. For on-chain challenges, the interactive challenge protocol does not only reduce on-chain cost, but also improve the robustness of the protocol.

## Goshen Architecture

<figure><img src="https://542266704-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPhvvuZOH3QTe19qFR0J5%2Fuploads%2Fgit-blob-26c8000ebd5711407bee8cf49818563a0f29dedc%2Fgoshen-structure%20(1).svg?alt=media" alt=""><figcaption><p>Rollup Architecture</p></figcaption></figure>

<figure><img src="https://542266704-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPhvvuZOH3QTe19qFR0J5%2Fuploads%2Fgit-blob-ee5db723923c8e60521f6c2adf5eadc067213cb2%2Fgoshen-riscv.svg?alt=media" alt=""><figcaption><p>Goshen State Transition</p></figcaption></figure>


---

# 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://docs.goshen.network/readme.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.