AI Foundations
A hands-on introduction to how modern AI actually works : LLMs, prompting, RAG, fine-tuning, agents with live notebooks, curated videos, and a real build-your-own-agent capstone.
beginner level · 9 modules
- LLM & Tokenization Fundamentals
- What is a large language model (LLM) ?
- Tokenization explained
- Tokenization playground
- Embeddings and the vector space of meaning
- Embedding similarity lab
- Prompt Engineering
- What is Prompt Engineering ?
- Zero-shot vs few-shot prompting
- Zero-shot vs few-shot lab
- Chain-of-thought and reasoning prompts
- Chain-of-thought lab
- System prompts and role conditioning
- Prompt playground
- Retrieval-Augmented Generation (RAG)
- Why LLMs hallucinate and need retrieval
- Vector databases explained
- Chunking strategies
- Chunking lab
- RAG architecture walkthrough
- Build a mini RAG pipeline
- Evaluating RAG quality
- RAG evaluation lab
- Fine-Tuning & Model Customization
- Fine-tuning vs RAG vs prompting
- LoRA and PEFT explained simply
- Fine-tuning lab
- LLM Evaluation, Security & Production
- Evaluation and testing for LLM apps
- Build a simple eval harness
- Prompt injection and LLM security basics
- Caching, rate limiting and cost management
- Guardrails and safety patterns
- AI Agents
- What is an agent?
- Tools and function calling
- TThought, action, observation — the ReAct cycle
- Build your first agent
- Multi-agent systems
- Extend your agent
- Coding Agents & Real-World Workflow
- What makes an agentic coding tool different from c
- Agentic coding workflows: plan, execute, review
- Use your first coding agent
- Build a RAG-powered agent from scratch
- Code review agent