# KodeKloud: Beta Courses AI Agents Fundamentals

## AI Agents Fundamentals

### AI Agents - Part 1

- [Introduction to AI Agents](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Introduction-to-AI-Agents/page.md): Hands-on overview of AI agents and related technologies including tokens, embeddings, RAG, vector databases, orchestration libraries, MCPs, and practical end-to-end project for building robust AI applications.
- [How LLMs work in real time](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/How-LLMs-work-in-real-time/page.md): Explains how large language models use context windows in real time and practical methods to enable accurate queries over private documents using chunking, embeddings, vector search, and RAG.
- [Embeddings Vector Representations](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Embeddings-Vector-Representations/page.md): How text embeddings map meaning to vectors enabling semantic search, document retrieval, and LLM grounding for robust paraphrase-insensitive search and recommendations
- [How LangChain works](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/How-LangChain-works/page.md): Explains how LangChain composes LLMs, embeddings, vector stores, memory, and tools to build retrieval augmented conversational agents and workflows for production chatbots
- [Practice Labs Your First AI API Call](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Practice-Labs-Your-First-AI-API-Call/page.md): Tutorial guiding users through setting up the OpenAI Python client, making chat API calls, extracting responses, and estimating token usage and costs
- [Practice Labs LangChain](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Practice-Labs-LangChain/page.md): Hands-on LangChain tutorial demonstrating environment checks, reducing SDK boilerplate, multi-model A/B testing, prompt templates, output parsers, and chain composition for building LLM pipelines
- [Prompt Engineering Techniques](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Prompt-Engineering-Techniques/page.md): Guide to crafting prompts for TechCorp's AI assistant covering techniques, role and format specification, examples, and best practices to improve output quality and consistency
- [Practice Labs Master Prompt Engineering](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-1/Practice-Labs-Master-Prompt-Engineering/page.md): Guide to mastering prompt engineering with LangChain using zero-shot, one-shot, few-shot, and chain-of-thought techniques with practical examples and best practices

### AI Agents - Part 2

- [Vector Databases Deep Dive](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Vector-Databases-Deep-Dive/page.md): Describes how embeddings and vector databases power semantic search and RAG, including chunking, similarity metrics, indexing options, and deployment trade offs for production
- [Practice Labs Build Semantic Search Engine](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Practice-Labs-Build-Semantic-Search-Engine/page.md): Guide to building a production-ready semantic search engine using embeddings, document chunking, ChromaDB and LangChain, with examples for embedding creation, indexing, and similarity search.
- [RAG](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/RAG/page.md): Explains Retrieval-Augmented Generation combining vector retrieval and context injection to provide accurate, up-to-date LLM answers from private documents with engineering guidance.
- [Practice Labs RAG Implementation](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Practice-Labs-RAG-Implementation/page.md): Guide to building a Retrieval-Augmented Generation pipeline using ChromaDB, sentence-transformers, smart chunking, prompt engineering, and LLM integration for grounded answers with source attributions.
- [LangGraph for AI Workflows](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/LangGraph-for-AI-Workflows/page.md): Describes LangGraph extending LangChain to orchestrate stateful, multi-node AI workflows with conditional branching, loops, shared typed state, and reusable nodes for complex tasks like compliance analysis
- [Practice Labs Build Stateful AI Workflows](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Practice-Labs-Build-Stateful-AI-Workflows/page.md): Guide to building stateful AI workflows using LangGraph including nodes, routers, tool integrations and a research agent example
- [Model Context Protocol](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Model-Context-Protocol/page.md): Describes the Model-Context-Protocol for letting AI agents call registered service endpoints with typed schemas to integrate external systems without custom code
- [Practice Labs Advanced MCP Concepts](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Practice-Labs-Advanced-MCP-Concepts/page.md): Guide to using MCP with LangGraph to expose and integrate external tools and multi-server orchestration for agents, including setup, calculator server, tool schemas, and examples.
- [Conclusion](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/AI-Agents-Part-2/Conclusion/page.md): Blueprint for building a context-aware document search agent using RAG, vector databases, orchestration, model management, and prompt engineering to improve enterprise knowledge access

### Introduction 

- [Course Introduction](https://notes.kodekloud.com/docs/AI-Agents-Fundamentals/Introduction/Course-Introduction/page.md): Hands-on course teaching semantic search, RAG, vector databases, and graph-based stateful AI agents with labs, code examples, and production deployment practices.