# Eval Engine

### Overview

<figure><img src="https://1992777252-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwoLAzTGcwgu5hRffYGQi%2Fuploads%2FAoBPtnEzGyUibjvpNgJx%2FX_logo.png?alt=media&#x26;token=1540a0c6-47ab-4ce9-ae11-4e7522154eb3" alt="" width="188"><figcaption><p>Eval Engine</p></figcaption></figure>

Eval Engine is a decentralized framework for evaluating AI agents with a focus on crypto-native agents.&#x20;

> Built on Chromia blockchain - a gas-free relational blockchain that enables seamless user experience without transaction fees.&#x20;

The system consists of three key components:

1. **Chromia Blockchain**: Acts as a transparent, immutable, gas-free database
2. **Engine**: The evaluation service
3. **Client**: The end user requesting evaluations

### Think of it as a Distinguished Food Critic

<figure><img src="https://1992777252-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwoLAzTGcwgu5hRffYGQi%2Fuploads%2FUrawA2iz9nC2iLr2SHFf%2Fimage.png?alt=media&#x26;token=84b9853c-ddef-43a1-9084-6986aabe25de" alt=""><figcaption><p>Eval Engine is like a Distinguished Food Critic</p></figcaption></figure>

Eval Engine is like a World-Renowned Food Critic. While their evaluation criteria remain private, their final ratings and reviews are public and immutable. Eval Engine works similarly - it processes evaluations through multiple specialized models but records all results transparently on Chromia blockchain. Like a prestigious restaurant rating that can't be bought or manipulated, Eval Engine ensures evaluation integrity through blockchain technology.


---

# 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://eval-engine.gitbook.io/eval-engine/eval-engine.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.
