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

# Configure the agent

The agent analyzes markets continuously and executes eligible decisions within configured limits. It runs in Deryve’s cloud infrastructure.

### Enable autonomous operation

After configuration, enable the agent to begin continuous operation. It keeps analyzing, executing, managing, and closing positions while your browser and device are offline.

There is no manual or per-trade approval mode. Risk controls apply to every agent action.

### Configuration fields

| Setting               | Purpose                                                     |
| --------------------- | ----------------------------------------------------------- |
| Model                 | Selects the analysis style and context profile              |
| Maximum position size | Caps single-trade USD notional                              |
| Maximum leverage      | Caps requested leverage                                     |
| Risk style            | Adjusts sizing behavior                                     |
| Require stop loss     | Blocks proposals without a stop                             |
| Daily loss limit      | Pauses agent activity after realized losses reach the limit |
| Custom instructions   | Adds preferences without overriding risk controls           |

### Monitor an agent

1. Enable the configured agent.
2. The agent scans available market data continuously.
3. Review its action, regime, confidence, rationale, and invalidation.
4. Track open positions, exits, and risk events from the activity feed.

The activity feed records analyses, executions, position actions, closes, and risk outcomes. A `HOLD` or `NO_TRADE` result is a valid outcome, not a failure.

{% hint style="warning" %}
Cloud automation does not remove market risk. Your configured boundaries control the agent’s permitted exposure.
{% endhint %}


---

# 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.deryve.xyz/ai-agent/configure-the-agent.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.