> ## Documentation Index
> Fetch the complete documentation index at: https://genai.codewithsiva.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic AI

> Build autonomous agents capable of reasoning, using tools, and collaborating to solve complex tasks

Welcome to the **Agentic AI** module. Step beyond static prompts and sequential pipelines to build autonomous systems that use reasoning loops, invoke external tools, and collaborate to achieve complex objectives.

## 💻 Module Practice Notebooks

Master all the concepts from this module with hands-on practice (excluding MCP):

* **Practice in VS Code**: Open the notebook in your local editor. Requires a local `.env` file containing your API keys.
* **Practice in Google Colab**: Open the notebook directly in Colab. Setup cells are included to install packages and request API keys.

[💻 VS Code](vscode://file/Users/sivaprasad/Downloads/GenAI%20With%20Python/public/notebooks/agentic-ai/agentic-practice-vscode.ipynb) | [🚀 Colab](https://colab.research.google.com/github/prasad230776/genai-course/blob/master/public/notebooks/agentic-ai/agentic-practice-colab.ipynb) | <a href="/public/notebooks/agentic-ai/agentic-practice-vscode.ipynb" download>📥 Download Notebook</a>

## 🗺️ Module Overview

Transition from static pipelines to fully autonomous agents:

```mermaid theme={null}
graph TD
    A["Agent Architectures<br/>(Autonomy, Loops, & Tools)"]
    --> B["Function Calling<br/>(API & Execution Integration)"]
    --> C["Multi-Agent Frameworks<br/>(Orchestration & Communication)"]
    --> D["Practical Capstone<br/>(Autonomous Support Agent)"]
```

## 📚 Module Curriculum & Roadmap

Explore the sections in this module using the cards below:

<CardGroup cols={2}>
  <Card title="1. Introduction to Agents" icon="handshake" href="/agentic-ai/01-introduction">
    Compare static chains and autonomous agents, explore planning and memory systems, and study the ReAct reasoning-action loop pattern.
  </Card>

  <Card title="2. Tool Use & Function Calling" icon="gears" href="/agentic-ai/02-function-calling">
    Understand the API function calling payload contract, declare tools using the `@tool` decorator, and bind tools to chat models.
  </Card>

  <Card title="3. Building a ReAct Agent" icon="robot" href="/agentic-ai/03-react-agent">
    Construct a complete working ReAct agent using LangGraph. Connect calculation tools and data directory tools to solve complex queries.
  </Card>

  <Card title="4. Multi-Agent Orchestration" icon="network-wired" href="/agentic-ai/04-multi-agent">
    Study multi-agent communication patterns, separation of concerns, and analyze CrewAI, LangGraph, and AutoGen orchestration frameworks.
  </Card>

  <Card title="5. Stateful Multi-Agent Application" icon="id-card-clip" href="/agentic-ai/05-resume-analyser">
    Build a custom, stateful Resume Analyzer & Interview Planner pipeline using LangGraph nodes, shared states, custom keyword checking tools, and a MemorySaver checkpointer.
  </Card>

  <Card title="6. Stateful Travel Assistant Project" icon="plane-departure" href="/agentic-ai/06-travel-assistant">
    Construct a stateful Travel Assistant (Weather Advisory & Budget Planner) graph manually. Build custom nodes, bind search tools, and compile with persistent thread memory.
  </Card>

  <Card title="7. Model Context Protocol (MCP)" icon="plug" href="/agentic-ai/07-mcp-introduction">
    Understand the requirement for MCP, its architecture (Host, Client, Server), and connect to the official GitHub MCP server to query repo details in Python.
  </Card>

  <Card title="8. Creating a Custom MCP Server" icon="terminal" href="/agentic-ai/08-custom-mcp-server">
    Build a custom FastMCP Python Math Server exposing calculator tools, connect a stdio transport subprocess, and bind them dynamically to a Gemini Chat Agent.
  </Card>
</CardGroup>

## 🛠️ Practical Capstone Project

### Autonomous Customer Support Agent

Build a multi-tool agent that handles user tickets:

1. **Tool 1: DB Lookup**: Queries database to fetch user account status and order details.
2. **Tool 2: KB Search**: A mini RAG system to search company policies/knowledge base.
3. **Tool 3: Email Sender**: Mock-sends an email update to the user.
4. **The Agent**: Receives a complaint (e.g., "Where is order #1002?"), reasons about which tool to call, fetches details, checks shipping status policies, sends a resolution email, and answers the customer.