> For the complete documentation index, see [llms.txt](https://docs.tradesurge.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tradesurge.co/platform/surgeai.md).

# SurgeAI

SurgeAI is the trading copilot inside TradeSurge. You describe your edge in plain language, and it helps turn it into a strategy you can test and deploy.

SurgeAI is the copilot that sits across the whole TradeSurge loop. You describe your edge in plain language. SurgeAI helps turn it into a structured strategy, backtest it and, later, deploy it as a trading agent.

{% hint style="info" %}
**Coming soon.** SurgeAI is not live yet. This page describes where it is heading.
{% endhint %}

## What ships first

SurgeAI arrives in three stages.

| Name                    | What it means                                                                                                                                                                                    |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **1. Review copilot**   | Read-only. Explains your accounts and trades in R, flags execution drift such as a lagging account, missed copies, slippage by firm and rules getting close, and suggests one refinement a week. |
| **2. Setup copilot**    | Takes your TradingView alert and your firms, then configures accounts, risk dials, the portfolio guard and the webhook for you to approve.                                                       |
| **3. Strategy builder** | The long-term vision below: plain language to a tested strategy.                                                                                                                                 |

## From idea to strategy (long-term vision)

{% stepper %}
{% step %}

### Describe your edge

Tell SurgeAI what you trade in your own words, such as the setup, the market, the entry, the stop and the exit.
{% endstep %}

{% step %}

### Review the draft

SurgeAI drafts a structured strategy on the Strategy API and lists its assumptions. You edit or approve it.
{% endstep %}

{% step %}

### Test it

The approved version is backtested and simulated against your firm's rules, like any uploaded strategy.
{% endstep %}

{% step %}

### Deploy it

A strategy that clears the promotion ladder can run as a trading agent on your accounts.
{% endstep %}
{% endstepper %}

## SurgeAI drafts, you decide

SurgeAI never places a trade. No AI output can reach the order path in TradeSurge. Everything SurgeAI produces is a draft you approve, and an approved strategy still passes the backtest, the simulator and the promotion ladder before it trades.

## Where SurgeAI helps

| Name        | What it means                                                 |
| ----------- | ------------------------------------------------------------- |
| **Prepare** | Turn a plain-language edge into a testable strategy.          |
| **Execute** | Explain a refused leg or a warning in plain language.         |
| **Review**  | Summarise your Journal and point to the setups costing you R. |
| **Refine**  | Suggest what to test next, and why.                           |

{% hint style="info" %}
SurgeAI strengthens the core job: running one proven strategy across more accounts. It does not replace your judgment or your edge.
{% endhint %}

## Next steps

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Strategies</strong></td><td>What a SurgeAI draft becomes.</td><td><a href="/platform/strategies.md">Strategies</a></td></tr><tr><td><strong>How order safety works</strong></td><td>Why AI output never reaches an order.</td><td><a href="/concepts-and-reference/order-safety.md">How order safety works</a></td></tr></tbody></table>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.tradesurge.co/platform/surgeai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.