RAG, AI Apps, and AI Agents for Cybersecurity and Networking

5h 21mIntermediate2025-09-10

Authors

Pearson

Omar Santos

Course details

This four-hour course shows you how to harness the power of Large Language Models (LLMs) for both offensive and defensive cybersecurity operations, as well as networking implementations. Gain the practical skills that are reshaping today’s cybersecurity and networking landscape. Learn fundamental RAG concepts and progressively build toward sophisticated agent-based implementations using industry-standard frameworks like LangChain, AutoGen, and LangGraph.

This course goes beyond theoretical concepts, offering hands-on experience with real-world step-by-step AI coding examples. Whether you're a red team operator looking to develop more sophisticated attacks, a blue team analyst seeking to bolster defenses, a security researcher exploring the frontiers of AI in cybersecurity, or a networking professional in need of AI knowledge, this course provides the core basics and skills needed to stay ahead in today’s environments.

Learning objectives
Master the foundations and practical applications of RAG, Langchain, LangGraph, and LlamaIndex.
Compare and contrast traditional RAG, RAG Fusion, and RAPTOR implementations for optimal information retrieval and processing.
Explore real-world case studies and hands-on demonstrations of AI-enhanced security and networking operations.
Discover how to implement RAG for dynamic information retrieval, re-ranking, and advanced automation in cybersecurity and networking scenarios.

Skills covered

Natural Language Processing (NLP)Incident ResponseAI Productivity ToolsArtificial Intelligence FoundationsArtificial Intelligence for BusinessNetwork AdministrationCybersecurityArtificial Intelligence (AI)Network and System AdministrationBusiness Software and ToolsOne-Off

Concepts

0. Introduction

01 - AI agents and agentic RAG for cybersecurity - Introduction

1. Introduction to RAG in Cybersecurity

02 - Learning objectives
03 - Introduction to retrieval-augmented generation (RAG)
04 - Exploring the GitHub repositories and additional resources
05 - Embeddings and embedding models
06 - Indexing techniques
07 - Vector databases
08 - Chunking strategies
09 - RAG vs. fine-tuning
10 - RAG, RAG fusion, and RAPTOR
11 - Running open-weight models with Ollama
12 - Exploring Open WebUI and other Ollama plugins
13 - Introduction to AI agents and agentic implementations
14 - Introduction to agentic RAG
15 - Introducing the Model Context Protocol (MCP)
16 - Introducing A2A and AGNTCY

2. Introducing LangChain, LangGraph, and LlamaIndex

17 - Learning objectives
18 - Introducing LangChain
19 - LangChain vs. LlamaIndex
20 - Prompt templates and system prompts
21 - Introducing LangSmith

3. Prompt Engineering, Prompt Chains, and RAG Examples

22 - Learning objectives
23 - Mastering prompt engineering
24 - Exploring basic prompt chain examples
25 - Creating prompt branching chains
26 - Exploring parallel prompt chains
27 - Creating a basic RAG application
28 - Creating a complete RAG application

4. AI Agents and Agentic Frameworks

29 - Learning objectives
30 - Introduction to AI agent frameworks
31 - Surveying CrewAI
32 - Introducing LangGraph
33 - Exploring examples of LangGraph in action
34 - Exploring an example of agents with MCP servers
35 - Securing agentic implementations

Conclusion

36 - AI agents and agentic RAG for cybersecurity - Summary