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

# Introduction

<figure><img src="/files/dwj08bBzM31aIpGVWfob" alt=""><figcaption></figcaption></figure>

**Helva** is an AI agent designed to drastically simplify access to DeFi. With Helva you can access EVM DeFi Ecosystems through a simple conversational interface. You can think of it like ChatGPT—but connected to your favorite wallet. Just type what you want to do, and confirm the transaction. That’s it. Helva may be used for the following goals (and not only):

* **Yields Automation & Optimization.**\
  Helva analyzes opportunities, selects the top APYs, and executes strategies with precision.
* **Trade Analyses & Execution.**\
  Helva runs in-depth analyses—technical, on-chain, and fundamental—across selected tokens, and can execute trades directly on Quickswap Perpetuals.
* **Tasks Automation.**\
  If you already know what to do but you want to save time, Helva is perfect for you. Just tell her in the prompt what to do, and she will perform the transactions across the integrated protocols.

Helva is built to deliver the following benefits to its users:

* **Time Saving.**\
  No more jumping between dozens of dApps to complete your operations on Base. All the protocols and features you need are already integrated with Helva—just call them from the prompt.
* **High Performances**.\
  Whether you're an experienced DeFi user or a beginner, Helva is for you. You can ask it to automatically execute a custom yield strategy you've designed, or let Helva create one for you, tailored to your token and risk profile.
* **Accessibility**.\
  Helva is easy to use, permissionless, multilingual, and anonymous. All you need to access it is  your favorite wallet.
* **Security.**\
  Helva leverages the smart contracts of robust infrastructures already existing, such as Quickswap, Aave, Morpho etc. she is just adding her brain on top of it.

Helva’s Core Features are the followin&#x67;**:**

* **Plan-To-Execute Architecture.**\
  This architecture allows Helva to *think* and *execute multiple tasks* within a single prompt. Unlike many other agents that can only perform one operation per user input (e.g., just a swap or just staking), Helva can analyze a message, break it down into multiple tasks, and autonomously execute them in sequence.
* **Interconnected.**\
  Helva is not just an on-chain operations agent. It can make decisions thanks to a robust off-chain infrastructure of APIs built around it. This enables Helva to access real-time data, market conditions, and much more when executing strategies.
* **EVM-Compatible.**\
  Helva has a modular, EVM-compatible architecture, making it easy to deploy across any EVM ecosystem and integrate new protocols or tokens. Any token can be used for basic operations (such as swaps or transfers) simply by referencing its smart contract address. Full integration of a token allows it to be invoked by its ticker and unlocks advanced functionalities.


---

# 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://helva.gitbook.io/helva/introduction.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.