Module 1: Introduction to AI & RAG Systems Slides

Slide Outline

1. Introduction to AI & RAG Systems - LLM fundamentals, hallucinations, and why retrieval-augmented generation changes everything
2. Learning Objectives - 4 outcomes for this module
3. Why This Module Matters - Every AI application that needs to answer questions about specific data — company docs, product manuals, legal contracts
4. How LLMs Work (The 5-Minute Version) - Lesson section from the full module
5. Tokens and Context Windows - Lesson section from the full module
6. Why LLMs Hallucinate - Lesson section from the full module
7. What RAG Changes - Lesson section from the full module
8. Types of RAG Systems - Lesson section from the full module
9. Real-World Use Cases - Customer support bots answering from product documentation, Legal AI searching case law and contracts
10. Common Mistakes to Avoid - 4 mistakes covered
11. Hands-On Labs - 2 hands-on labs
12. Key Takeaways - 5 points to remember

Learning Objectives

• Understand how LLMs work at a high level
• Learn about tokens, context windows, and their limitations
• Understand why LLMs hallucinate and how RAG solves it
• Compare vanilla LLM vs RAG responses

Why This Module Matters

Every AI application that needs to answer questions about specific data — company docs, product manuals, legal contracts, medical records — needs RAG. Without it, your chatbot confidently makes things up. With it, your chatbot cites real sources. This is the foundation of every production AI system.

Common Mistakes

• Building a chatbot without RAG and hoping the LLM knows your domain
• Stuffing the entire document into the prompt instead of retrieving relevant chunks
• Ignoring context window limits — overfilling the prompt degrades quality
• Not evaluating retrieval quality — bad retrieval means bad answers regardless of the model

Key Takeaways

• LLMs predict tokens based on training data — they do not know facts
• Hallucinations happen because the model generates plausible text without verification
• RAG retrieves relevant documents and injects them into the prompt before generation
• Context windows limit how much data you can include — retrieval selects the most relevant
• Three RAG levels: naive (demo), advanced (production), agentic (autonomous)

Hands-On Labs

1. Run Your First LLM Application

   Build a simple Python app that calls an LLM API.

   20 min - Beginner

   • Install the Anthropic Python SDK
   • Send a basic prompt to Claude
   • Observe the response and token usage
   • Ask a question about recent events and observe hallucination

   View lab files on GitHub

2. Compare Vanilla LLM vs RAG

   See the difference RAG makes on answer quality.

   25 min - Beginner

   • Ask the LLM a domain-specific question (without context)
   • Provide the same question with relevant document context
   • Compare accuracy, citations, and confidence
   • Discuss when RAG is necessary vs when vanilla LLM suffices

   View lab files on GitHub