> For the complete documentation index, see [llms.txt](https://guide.graphaidefi.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.graphaidefi.org/what-is-graph-ai.md).

# What is Graph AI

The worlds of on-chain finance and real world assets (RWA) are starting to converge. Advances in AI have birthed a thriving DeFAI sector where AI models and decentralized agents allow for the execution of seamless on-chain autonomous trading strategies. Simultaneously, RWAs are increasingly emerging as a robust source of yield within the DeFAI industry, with the RWA sector forecasted to grow to $30 trillion by 2030. The worlds of on-chain finance and real world assets (RWA) are starting to converge.

The Blockchain Open RAG Graph (Graph AI) introduces a revolutionary approach to blockchain data utilization, enabling developers and users to create powerful AI-driven decentralized applications (dApps). By indexing both historic and dynamic blockchain data, Graph AI facilitates the creation of customized sub-indexes stored in vector databases (Knowledge Graphs). These knowledge graphs act as extensions to LLMs access to contextual and blockchain-specific information to formulate scalable web3 applications.

This innovation opens up new possibilities for leveraging blockchain data in AI and machine learning applications.


---

# 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://guide.graphaidefi.org/what-is-graph-ai.md?ask=<question>&goal=<endgoal>
```

`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.