# AI Tools

**AI Tools** are external capabilities that Skynet Agents can call on to complete tasks. Unlike agents, tools don’t think or decide—they simply execute. Think of them as APIs with structure and purpose, each one mapped directly to a service, organization, or brand.

Whether it’s **Booking.com** for travel reservations, **WeatherAPI** for real-time forecasts, or **Solana** for blockchain interactions, tools represent trusted, outcome-driven functions. Agents don’t need to understand *how* the service works—only that it can be called when needed, with the right inputs, to deliver a specific result.

Each tool is associated with a real-world organization or platform. When a Skynet Agent invokes a tool, it’s not abstract computation—it’s triggering a real action through a real provider. These providers receive **direct payment for the service rendered**, automatically handled by the Skynet Chain using stablecoins or other supported currencies.

Skynet ensures that tools are **standardized, discoverable, and interoperable**. Developers and organizations define clear interfaces and usage terms, making it simple for agents to connect and orchestrate across services. Tools don’t hold state, don’t store data, and don’t act unless explicitly invoked—ensuring security, predictability, and composability across the network.

In short, AI Tools on Skynet are the bridge between intelligent agents and real-world outcomes—connecting autonomous logic with the power of trusted digital services.

{% hint style="warning" %}
A live list of accessible tools is available via our developer dashboard and will also become available in the Agent Studio.
{% endhint %}


---

# Agent Instructions: 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://documentation.skynet.io/skynet/getting-started/features/ai-tools.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.