This repository is a hands-on, beginner-friendly guide to building Generative AI products and AI agents.

If you are:

• New to Generative AI
• Curious about AI agents
• A product manager, developer, or learner who wants to understand how real GenAI systems are built

👉 This repo is all you need to get started.

The focus is learning by building, not theory.

• Beginners in Generative AI
• Product Managers learning GenAI & AI Agents
• Developers starting with LLMs, RAG, and Agents
• Anyone who wants practical, runnable projects

You do NOT need deep ML knowledge to start.

By going through these projects, you’ll learn:

• How LLMs work in real products
• How to build AI agents (single-agent & multi-agent)
• How RAG (Retrieval Augmented Generation) works
• How agents use tools, APIs, and workflows
• How to think like a GenAI Product Builder

Each folder is a self-contained learning project 👇

Generative-AI-Projects/
│
├── agents/
│   ├── Agentic_Rag_Langchain/
│   ├── Competitor analysis agent/
│   ├── Customer support agent/
│   ├── Market_Research_agent/
│   ├── MCP Powered agents/
│   │   └── travel-agent/
│   ├── News TL;DR agent/
 │   ├── Research Team AutoGen/
│   ├── Travel agent/
│   ├── Youtube Trend analysis/
│   ├── n8n agents/
│   └── personal Finance agent/
│
├── LICENSE
└── README.md

Learn how to:

• Combine LLMs + vector search
• Build an agentic RAG pipeline
• Answer questions from documents intelligently

Concepts: RAG, embeddings, vector DBs, LangChain

An AI agent that:

• Analyzes competitors
• Summarizes strengths, weaknesses, and positioning

Concepts: Research agents, web data, structured outputs

An intelligent customer support agent that:

• Categorizes customer queries (Technical, Billing, General)
• Analyzes sentiment (Positive, Neutral, Negative)
• Routes queries to appropriate handlers
• Escalates negative sentiment queries to human agents

Concepts: LangGraph workflows, state management, query routing, sentiment analysis

Automates:

• Market research
• Trend analysis
• Insight generation

Concepts: Prompt engineering, research workflows, agent planning

A multi-agent system that:

• Plans trips
• Uses tools
• Coordinates multiple agents

Concepts: Multi-agent systems, MCP, orchestration, tool calling

A role-based AutoGen multi-agent system that:

• Uses an Admin, Planner, Developer, Executor, and QA agent
• Controls collaboration with explicit speaker transition rules
• Supports reproducible research-style workflows
• Visualizes agent interaction flow as a graph

Concepts: AutoGen group chat, multi-agent governance, role prompts, tool execution, QA loops

A simpler version to understand:

• How a single AI agent works
• How it plans and responds

Concepts: Agent basics, reasoning loops

An agent that:

• Fetches current news articles from NewsAPI
• Scrapes article content from web pages
• Generates concise TL;DR summaries
• Provides relevant news based on user queries

Concepts: News APIs, web scraping, async processing, LangGraph workflows, concurrent LLM calls

An agent that:

• Pulls YouTube data
• Analyzes trends
• Summarizes insights

Concepts: APIs, data analysis with LLMs

Low-code AI agents built using n8n workflows.

Concepts: Automation, agent workflows, no-code / low-code AI

An AI agent that helps with:

• Expense understanding
• Financial insights

Concepts: Domain-specific agents, reasoning, structured prompts

1. Clone the repo

   git clone https://github.com/SriLaxmi1993/Generative-AI-Projects.git

2. Pick one folder (don’t try everything at once)

3. Read the code + prompts

4. Run the project

5. Modify prompts and logic → learn by experimenting

If you're a beginner, follow this order:

1. Travel Agent (single agent)
2. Customer Support Agent
3. Market Research Agent
4. Competitor Analysis Agent
5. News TL;DR Agent
6. Agentic RAG
7. Multi-Agent Travel Agent (MCP)
8. Research Team AutoGen (Multi-Agent Group Chat)
9. n8n Agents

Built by Sri Laxmi AI Product Manager with 8+ years of experience

• Built & scaled Generative AI products to 4M+ users
• Creator of Product Management Interview Expert GPT (15,000+ users)
• Passionate about helping people upskill in GenAI
• Building practical, real-world AI projects for learners

🌐 AI Learning Hub: https://ai-knowledge-management-plum.vercel.app/

If this repo helps you:

• ⭐ Star the repo
• 🍴 Fork it
• 🧠 Experiment and learn

Pull requests and improvements are welcome.

This repo is intentionally practical, simple, and beginner-focused.

The goal is not to impress — The goal is to help you build real GenAI products confidently.

Happy building! 🤖✨

If you want, next I can:

• Add mini READMEs inside each agent folder
• Create a “GenAI for Product Managers” learning path
• Optimize this README for GitHub stars & discoverability

Just tell me 👍