> For the complete documentation index, see [llms.txt](https://guida-2.gitbook.io/guida-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guida-2.gitbook.io/guida-docs/core-concepts/autonomous-agents.md).

# Autonomous Trading Agents

## What is an autonomous trading agent?

An **autonomous trading agent** is software that carries out a trading strategy on your behalf, without needing you to press the button each time. You define the strategy and its limits; the agent handles the relentless, around-the-clock work of monitoring the market and acting when your conditions are met.

Guida is that agent. But "autonomous" is a word that deserves careful unpacking, because it can suggest something Guida deliberately is *not*.

## Autonomous ≠ out of your control

There's a spectrum of how much freedom a trading system has:

| Model                      | Who decides what to trade?                             | Guida?           |
| -------------------------- | ------------------------------------------------------ | ---------------- |
| **Manual**                 | You, every single time.                                | —                |
| **Rules-based automation** | You define the rules; the agent executes them exactly. | ✅ This is Guida. |
| **Fully discretionary AI** | The system decides on its own what to buy and sell.    | ❌ Not Guida.     |

Guida sits deliberately in the middle. The **intelligence** is in helping you *design and test* a strategy — translating your words into precise logic, and showing you how it behaves. The **execution** is strictly bounded by the rules and limits you set. Guida doesn't wake up and decide to do something you didn't ask for. It is tireless and disciplined, not independent.

This is by design. An agent you can't predict is an agent you can't trust with your money. Guida aims to be completely predictable: it does what your strategy says, within your guardrails, every time.

## Why automate at all?

Three reasons, and they're the same reasons professional desks have run automated systems for decades:

1. **Availability.** Markets — especially crypto and on-chain assets — run 24/7. No human can. An agent can watch every hour of every day.
2. **Discipline.** The hardest part of trading isn't knowing what to do; it's *doing it* when fear or greed says otherwise. An agent has no emotions to override. It sells at your take-profit and cuts at your stop-loss without flinching.
3. **Speed and consistency.** When your conditions are met, the agent acts immediately and identically every time — no hesitation, no second-guessing, no "I'll wait just a bit longer."

Automation doesn't make a bad strategy good. But it makes a good strategy *executable* — reliably, at scale, over time.

## Where the "AI" fits

The AI in Guida works for you at the *design and understanding* layer:

* **Understanding intent** — turning your plain-English description into structured, correct trading logic.
* **Helping you test** — running and summarizing backtests and paper trades so you can judge an idea quickly.
* **Speaking each asset's language** — as Guida expands to tokenized real-world assets, understanding that different asset classes behave differently.

The AI helps you build a strategy you understand and trust. It does not quietly take the wheel. That separation — smart help, bounded execution — is the heart of how Guida is built.

***

**Next:** [Strategies →](/guida-docs/core-concepts/strategies.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://guida-2.gitbook.io/guida-docs/core-concepts/autonomous-agents.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.