# Assets

## Selecting assets

When you create an agent, you specify **which assets it should operate on**. There are several ways to do this:

* **Mention them directly in your description** — e.g. "DCA $200 into Bitcoin every Friday".
* **Select them in the chat** through the **Add** → **Assets** button: browse the catalog (10,000+ instruments) and attach them to the conversation.
* **Pick them from your broker** — if you've connected a platform, you can choose the assets available at that broker.

{% hint style="info" %}
You can **mix asset classes** within a single agent: stocks, cryptos, currencies, indices, futures, ETFs, commodities.
{% endhint %}

## Available asset categories

More than **10,000 instruments** are available, organized by category:

* **Stocks** (Apple, Tesla, Nvidia, etc.)
* **Cryptos** (Bitcoin, Ethereum, etc.)
* **Currencies** (EURUSD, USDJPY, etc.)
* **Indices** (S\&P 500, Nasdaq, CAC 40, etc.)
* **Commodities** (gold, oil, etc.)
* **ETFs**
* **Futures**

The **number of assets per agent** depends on your subscription plan. See [Pricing](/misc/pricing.md).

***

## Execution target per asset

When you launch a **backtest** or an **execution**, Obside asks you, for each asset referenced in the agent, **on which exchange or broker** the operation should be simulated or executed.

This lets a single agent run on different platforms depending on your connected accounts, with the fees and market specifications proper to each broker.

{% hint style="success" %}
For backtests, you can also choose the **Historical** option to use Obside's warehouse data, without depending on a specific exchange.
{% 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.obside.com/agents/create-an-agent/assets.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.