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

# Carotte AI

Carotte AI is a platform designed for the Web3 and decentralized finance (DeFi) ecosystems, centered around user interaction with autonomous AI agents. The system's primary objective is to process complex data streams (social media, market data, on-chain metrics) to provide users with actionable insights and automated trading capabilities. The entire architecture of the platform is built upon the DeFAI concept.

#### **Core Concept: DeFAI**

DeFAI is the core philosophy and architectural principle of the Carotte AI platform. This concept refers to the programmatic fusion of analytical intelligence generated by artificial intelligence (AI) with actions on decentralized finance (DeFi) protocols. DeFAI closes the loop between research and execution, offering users a seamless experience.

* **Artificial Intelligence (AI) Layer:** This layer comprises data analysis, prediction, and decision-support systems. Agents like Sentinel detect market sentiment and trends, while Carotte Chat serves as an interface for in-depth research and analysis of this data. This layer answers the "what" and "why."
* **Decentralized Finance (DeFi) Layer:** This layer provides execution and implementation capabilities. Tools like Carotte Swap allow insights generated by AI or user commands to be executed directly on-chain in a non-custodial manner. This layer solves the "how" by performing actions such as trading and bridging.

Carotte AI's DeFAI approach makes sophisticated financial strategies accessible through natural language commands and autonomous agents, significantly lowering the barrier to entry for Web3.

## Quick links

{% content-ref url="/pages/6BaGul3RRipYnOn3jZIl" %}
[System Overview](/system-overview-1/core-philosophy-defai.md)
{% endcontent-ref %}

{% content-ref url="/pages/KvgnPp6VArfSu8ePqwpM" %}
[Products](/products/luigi.md)
{% endcontent-ref %}

{% content-ref url="/pages/bYY06HV2YiviQuza3xDv" %}
[Nerds](/nerds/technical-infrastructure-and-devops-architecture.md)
{% endcontent-ref %}

{% content-ref url="/pages/da00jztLNFYMe08P7AzW" %}
[Other Documentation](/other-documentation/tokenomics.md)
{% endcontent-ref %}

{% content-ref url="/pages/PlFl7ef3T8eyceD6utah" %}
[Broken mention](broken://pages/PlFl7ef3T8eyceD6utah)
{% endcontent-ref %}


---

# 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://docs.carotte.ai/carotte-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.