1
What Is Generative AI?
Understand what generative AI is, how it differs from traditional AI, and why it matters across writing, coding, design, and business workflows.
Read lessonPractical tutorial track
Generative AI and LLM Applications
This 30-lesson tutorial series takes learners from first principles to production-ready design. It covers prompting, embeddings, RAG, tool use, agents, multimodal systems, monitoring, private AI, and responsible deployment. Each lesson includes clear explanations, examples, a coding section, key takeaways, and exercises.
Beginner to advanced
Examples in every lesson
Python coding walkthroughs
Production-focused topics
30Detailed lessons
3Learning stages
ExamplesPractical use cases throughout
PythonClear coding sections
Stage 1
Beginner lessons
Start with the language of generative AI, how models work, how prompting works, and how to use these systems safely and effectively.
2
How Large Language Models Work at a High Level
Learn the basic idea behind large language models, including pretraining, next-token prediction, and why these models can generate fluent text.
Read lesson3
Tokens, Context Windows, and Prompts
Understand how text is split into tokens, why context windows matter, and how prompt size affects quality and cost.
Read lesson4
System Prompts and Instruction Hierarchy
Learn how system instructions, developer instructions, and user prompts interact to shape model behavior.
Read lesson5
Temperature, Sampling, and Output Control
Understand how generation settings affect creativity, consistency, and determinism in outputs.
Read lesson6
Foundation Models vs Task-Specific Models
Compare broad foundation models with smaller or narrower models designed for particular tasks or domains.
Read lesson7
Common Generative AI Use Cases
Explore real-world uses of generative AI in education, business, software, content creation, and operations.
Read lesson8
Prompt Engineering Basics
Learn the foundational habits of writing prompts that are clearer, more consistent, and easier to evaluate.
Read lesson9
Structuring Better Prompts with Role, Context, and Examples
Go beyond simple instructions by using role prompts, context blocks, and few-shot examples to guide the model more effectively.
Read lesson10
Hallucinations, Limits, and Verification
Understand why generative AI can invent facts, what situations increase that risk, and how to design safer workflows.
Read lessonStage 2
Intermediate lessons
Move into the patterns that power serious applications: APIs, embeddings, vector search, RAG, evaluation, guardrails, and tool use.
11
Designing Simple Chatbots and Assistants
Learn the building blocks of chatbot design, including instructions, user input, fallback behavior, and conversation flow.
Read lesson12
Calling Models Through APIs
Learn how model applications connect to hosted APIs, including requests, parameters, and basic error handling.
Read lesson13
Embeddings and Semantic Similarity
Understand embeddings as vector representations of meaning and learn why they power search, clustering, recommendations, and RAG.
Read lesson14
Vector Databases and Semantic Search
Learn what vector databases do and how they make embedding search practical at scale.
Read lesson15
Retrieval-Augmented Generation (RAG) Basics
Understand the core RAG pattern: retrieve relevant information first, then ask the model to answer using that evidence.
Read lesson16
Chunking, Indexing, and Preparing Documents for RAG
Learn how document chunking affects retrieval and why indexing strategy matters for usable RAG systems.
Read lesson17
Building a Simple RAG App in Python
Bring retrieval and generation together in a basic Python workflow that can later be connected to real models and databases.
Read lesson18
Evaluating Generative AI Systems
Learn how to evaluate answer quality, groundedness, consistency, usefulness, and task success in generative AI applications.
Read lesson19
Guardrails, Safety, and Content Controls
Study practical ways to reduce harmful, unsafe, or out-of-scope output in real applications.
Read lesson20
Function Calling and Tool Use
Understand how models can call tools, APIs, calculators, or business functions instead of only returning plain text.
Read lessonStage 3
Advanced lessons
Finish with production architecture, agentic systems, multimodal workflows, optimization, monitoring, private AI, governance, versioning, and capstone planning.
21
Prompting vs RAG vs Fine-Tuning
Learn when to improve prompts, when to add retrieval, and when fine-tuning may be worth considering.
Read lesson22
Agents and Agentic Workflows
Learn what makes an agent different from a simple chatbot and how multi-step workflows are coordinated.
Read lesson23
Multimodal Models: Text, Image, Audio, and Beyond
Explore models that work across more than one data type and how multimodal design expands application possibilities.
Read lesson24
Cost, Latency, and Throughput Optimization
Learn how to balance speed, cost, and quality when usage grows from prototype to production.
Read lesson25
Deploying Generative AI Applications
Understand the architecture of production deployments, including frontend, backend, model access, storage, and security boundaries.
Read lesson26
Monitoring, Logging, and Observability
Learn what to measure in production so you can understand failures, improve quality, and manage operational risk.
Read lesson27
Security, Privacy, and Data Governance
Study the policies and technical controls needed to protect user data and reduce misuse in generative AI systems.
Read lesson28
Private and Local LLM Applications
Explore why teams use local models and private deployments, along with the trade-offs in hardware, speed, and control.
Read lesson29
Versioning Prompts, Models, and Workflows
Learn how versioning helps teams manage changes to prompts, models, retrievers, and validation rules over time.
Read lesson30
Capstone: Designing a Production-Ready Generative AI Application
Bring the course together by planning a complete generative AI application from use case to deployment, evaluation, and monitoring.
Read lessonSuggested subdirectory
A strong subdirectory for this tutorial is /generative-ai-llm/. It is clean, descriptive, and broad enough to cover prompting, RAG, agents, and real-world LLM applications.
Start with Lesson 1