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

# Before the start

basket.fund turns a creator’s market view into a basket that users can actually follow.

A basket is a weighted portfolio managed by a creator. It can include assets across supported networks, but from the user’s side it behaves like one position. The user does not need to buy each token manually, bridge between chains, calculate weights, or rebalance every time the creator changes their thesis.

They choose a basket, deposit USDC, and basket.fund handles the execution.

Under the hood, each basket holds real underlying assets. Users are tracked through basket units, which represent their share of the basket after their order has fully settled.

The goal is not to make every part of crypto invisible. Users should still understand what they are buying. The goal is to remove the repetitive execution work that usually sits between discovering a good thesis and actually getting exposure to it.

Every basket starts with a creator’s idea.

That idea can be broad, like “Solana DeFi blue chips,” or more specific, like “Base ecosystem assets with strong fee growth.” The creator chooses the assets, sets the target weights, and writes a thesis explaining why the basket exists.

A simple basket could look like this:

```
50% SOL
25% JUP
15% RAY
10% USDC
```

The weights show the creator’s intended exposure. They are targets, not a promise that the basket will stay at those exact percentages every second.

Markets move. Swaps have slippage. Users enter and exit. Rebalances take time to execute. Because of that, the live basket composition can drift slightly from the target weights until the next update or execution cycle.

This is normal. A basket is managed exposure, not a static screenshot.


---

# 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:

```
GET https://basket-fund.gitbook.io/basket.fund-docs/before-the-start.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.