> 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/getting-started/how-tradesurge-works.md).
# How TradeSurge works
TradeSurge has four building blocks. Learn them once and the rest of the manual makes sense.
TradeSurge has four building blocks. Learn them once and the rest of the manual makes sense.
## The four building blocks
{% stepper %}
{% step %}
### Accounts
An Account is one trading account at one prop firm. It holds the firm's rules, your phase (evaluation or funded), your balance and your risk dial.
{% endstep %}
{% step %}
### Rules & Limits
Rules & Limits are the firm's daily drawdown, maximum drawdown, profit target and daily reset. TradeSurge checks them before every trade, and Breach Guard steps in before a limit is hit.
{% endstep %}
{% step %}
### Terminal
The Terminal is where you trade by hand. One order is copied to every account you select, and each copy is sized from that account's own risk dial.
{% endstep %}
{% step %}
### Strategies
A Strategy is code you upload, in Python or Pine Script. You backtest it, stress-test it against a firm's rules, and later deploy it to autotrade.
{% endstep %}
{% endstepper %}
## How they fit together
You connect Accounts. Rules & Limits protect them. You trade them from the Terminal, or let a Strategy trade them for you. Every result is recorded in R on the Dashboard and in the Journal.
The loop is: **prepare, execute, review, refine.** SurgeAI (coming soon) will sit across the whole loop as a copilot, from shaping a strategy to reviewing its results.
## Two surfaces, one engine
The web app and Telegram both talk to the same engine. Telegram alerts open with the alpha. Trading from Telegram follows later.
{% hint style="info" %}
Everything in TradeSurge is measured in R, the amount you risk on a trade. Win rate and dollar figures never decide anything. See [R and expectancy](/concepts-and-reference/r-and-expectancy.md).
{% endhint %}
## Next steps
---
# 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/getting-started/how-tradesurge-works.md?ask=&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.