# School Agent Platform 🏫 A powerful, multi-agent educational platform built using Google ADK.

## School Agent Platform 🏫

<figure><img src="/files/Itx968EaruDAOdrZ1J0s" alt=""><figcaption></figcaption></figure>

<https://github.com/andriidrok-glitch/AIDevCamp2026_assignment>

A powerful, multi-agent educational platform built using **Google ADK**. The system uses an **Agent-to-Agent (A2A)** architecture where a central Root Agent (the Principal) orchestrates specialized subject teachers.

### 🌟 Key Features

* **Multi-Agent Architecture**: Dedicated agents for Math, English, Geography, and Computer Science.
* **Smart Routing**: Root agent identifies the user's intent and delegates to the correct specialist.
* **Integrated Tools**: Built-in `calculator` for complex mathematical expressions.
* **Contextual Memory**: Remembers conversation history for a seamless learning experience.

### 📂 Project Structure

* `school_agent/`: Root orchestrator agent.
* `math_agent/`: Specialist for Algebra, Geometry, and Calculus.
* `english_agent/`: Specialist for Grammar and Literature.
* `geography_agent/`: Specialist for Maps and Topography.
* `cs_agent/`: Specialist for Programming and Algorithms.
* `tools.py`: Utility functions like the calculator.

### 🚀 Getting Started

#### Prerequisites

* Python 3.10+
* Google API Key (Gemini 2.5 Flash supported)

#### Installation

1. Activate the virtual environment:

   ```
   .\.venv\Scripts\Activate.ps1
   ```
2. Install dependencies (if not already installed):

   ```
   pip install google-adk
   ```

#### Running the Agent

To start the interactive CLI:

```
adk run school_agent
```

To start the Web UI:

```
adk web --port 8000
```

***

*Built with ❤️ using Google Agent Development Kit.*

<figure><img src="/files/a4RIfrO9SmpqEeQMBhX6" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/fvGjUUemWov3LECdikGS" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/Knb5tffQZ5E308f8c5TR" alt=""><figcaption></figcaption></figure>


---

# 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://wtech-1.gitbook.io/ai-dev/school-agent-platform-a-powerful-multi-agent-educational-platform-built-using-google-adk..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.