> For the complete documentation index, see [llms.txt](https://birdytradebot.gitbook.io/birdyai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://birdytradebot.gitbook.io/birdyai/trading-modes/signal.md).

# Signal

The **Signal Mode** uses [**Birdy Signal**](https://t.me/BirdySignal), a bot that scans over 10,000 well-known callers in both public and private groups. By tracking their past performance and analyzing their latest calls, Birdy Signal helps identify the most profitable opportunities.

This mode allows you to automatically act on calls made by top-performing traders with proven success rates.

#### How It Works

1️⃣ **Call Aggregation**\
Birdy Signal tracks and ranks callers based on their historical performance using mathematical rules like the **Wilson Score**.

2️⃣ **Real-Time Alerts**\
As soon as a top-performing caller shares a new token, the bot will send out an alert. Each signal includes the caller’s **win rate**.

<figure><img src="/files/KaFgfuzlcbWgpZr4WU4K" alt="" width="375"><figcaption><p>Signal mode</p></figcaption></figure>

**Mode Configuration:**

When using Birdy Signal, you can configure the following buy conditions for the bot:

* **Win Rate**: Set a minimum win rate. For example, choosing **67%** ensures the bot trades only on signals from callers with at least 67% success in their previous calls. Higher win rates increase success chances but will result in fewer signals.
* **Market Cap**: Set a minimum market cap (e.g., **$50,000**) to trade only tokens with sufficient liquidity and reduce the risk of extreme volatility.

These settings are customizable to fit your trading strategy and risk preference.

{% hint style="info" %}
The bot does not automatically buy tokens that are not yet bonded on Pump.fun, even if Birdy Signal sends an alert for them based on calls from tracked callers.
{% 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:

```
GET https://birdytradebot.gitbook.io/birdyai/trading-modes/signal.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.