# Fractal

{% hint style="success" %}
First introduced at [NVIDIA GTC 2025](https://x.com/alphakek_ai/status/1901814335779074333), the world's most prestigious AI conference. It was one of just 170 breakthrough technologies globally recognized by NVIDIA.
{% endhint %}

<figure><img src="https://1848060412-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSO2Zvs9aj5evVm1aZjg6%2Fuploads%2F9NqfagPnzgqoUdfHJa8d%2FFrame%20485.png?alt=media&#x26;token=5a27c927-63b3-4c53-9354-0fb8ebe0f72e" alt=""><figcaption><p><a href="https://www.nvidia.com/gtc/posters/?search=alphakek#/">Showcased at NVIDIA GTC 2025.</a></p></figcaption></figure>

## **Overview**

***

At the core of AIKEK's technology stack lies Fractal, a first-of-its-kind knowledge engine. It is the culmination of AIKEK pioneer [Vladimir Sotnikov](https://www.alphakek.ai/#team)’s work in AI and machine learning, recognized by both [OpenAI](https://openai.com/blog/introducing-text-and-code-embeddings) and [NVIDIA](https://www.nvidia.com/en-us/on-demand/search/?facet.mimetype\[]=event%2520session\&facet.mimetype\[]=event%20session\&layout=list\&page=1\&q=Sotnikov\&sort=relevance\&sortDir=desc).

Fractal synthesizes 1M+ real-time data points, ranging from mainstream financial media to onchain events, handling up to 5x more information sources simultaneously compared to traditional AI models.

<figure><img src="https://1848060412-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSO2Zvs9aj5evVm1aZjg6%2Fuploads%2FcdBymXRDeHjh9BW92VcL%2FHorizontal%20Banner%402x.png?alt=media&#x26;token=32415539-bf02-4ce2-bd9a-cc4b4c91188b" alt=""><figcaption><p><a href="https://www.nvidia.com/gtc/posters/?search=alphakek#/">View on NVIDIA website.</a></p></figcaption></figure>

## **Capabilities**

***

<table><thead><tr><th width="254">Feature</th><th>Description</th></tr></thead><tbody><tr><td><strong>Diverse Data Integration</strong></td><td>Combines 1M+ data points from various financial and crypto sources.</td></tr><tr><td><strong>Enhanced Data Processing</strong></td><td>Capable of handling large-scale, frequently updated data by constructing dynamic knowledge engines.</td></tr><tr><td><strong>Web3-Specific Design</strong></td><td>Tailored specifically for cryptocurrency applications.</td></tr><tr><td><strong>Data Blending</strong></td><td>Integrates both on-chain data and external market data for comprehensive insights.</td></tr></tbody></table>

Fractal is future-proof: it's developed to be the ultimate crypto data environment for AI workflows, such as the [agent-swarm](https://docs.alphakek.ai/launch/ai-agents/agent-swarm "mention").

{% hint style="success" %}
To build your own custom AI knowledge engine, see [knowledge-swarms](https://docs.alphakek.ai/launch/knowledge-swarms "mention").
{% endhint %}


---

# 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.alphakek.ai/fractal.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.