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

# Strategy Orchestration

The selected model decides what to trade; Selaciti decides how much risk that decision is allowed to take, and how it reaches the market.

## From decision to action

* The highest-scoring model proposes an action with confidence and rationale
* Risk guards translate that into a bounded, budget-aware position
* Execution runs through Robinhood Agentic on the reserved account

## Risk and execution guards

* **Reserved budget:** The Creator Fee Vault trades only a set budget, never the full treasury
* **Exposure limits:** Per-asset and portfolio caps with volatility-scaled sizing
* **Loss controls:** Daily loss caps and rolling drawdown thresholds
* **Stop enforcement:** Stop-loss and take-profit with circuit breakers
* **Off switch:** The agent can be disconnected at any time from the app

## The role of the competition

Orchestration does not pick strategies by committee. It defers to whichever model currently holds the seat, then constrains that model's actions with hard guards. If a model's edge fades, its score falls and a different model takes over automatically.

See also: [Models and Selection](/architecture/models-and-rl.md) and [Robinhood Agentic](/architecture/robinhood-agentic.md).


---

# 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.selaciti.com/overview/strategy-orchestration.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.
