AI Tools: LLM & Prompt Engineering Mastery
AI Tools is Amol Shukla's hands-on learning hub for anyone who builds with or works alongside AI. Track 1 (LLM Course) takes you inside large language models: how they predict text, what the context window really is, how temperature and sampling control creativity, why hallucinations happen and how to stop them, and how agentic loops turn LLMs into autonomous workers — plus RAG, embeddings, and evaluation. Track 2 (Prompt Engineering Course) teaches the anatomy of effective prompts, zero-shot, few-shot, and chain-of-thought techniques, structured outputs, reusable templates, advanced reasoning (self-consistency, tree of thought, prompt chaining), real-world playbooks for code and content, prompt-injection safety, and evaluating prompts like an engineer — packed with worked examples. Every lesson includes notes, runnable code, visualization tips, and practice exercises.
Course Modules
Module 1: [LLM] How Large Language Models Work
LLM Course · Build a clear mental model of what an LLM is, how it predicts text, the transformer architecture, and how these models are trained.
Lesson 1: What Is an LLM?
Understand what large language models are, why they predict the next token, and the mental model that unlocks everything else.
Lesson 2: The Transformer & Self-Attention
Peek inside the model: embeddings, the transformer stack, and the self-attention mechanism that decides which words matter.
Lesson 3: The Training Pipeline — Pre-training, Fine-tuning & RLHF
How a raw neural network becomes ChatGPT: pre-training on trillions of tokens, supervised fine-tuning, and reinforcement learning from human feedback.
Module 2: [LLM] The Context Window
LLM Course · Learn what the context window is, why token limits matter, and how to work with documents longer than the window.
Lesson 4: What Is a Context Window?
The context window is everything the model can 'see' at once — input plus output. Understand limits, truncation, and memory.
Lesson 5: Managing Long Contexts
Chunking, sliding windows, summarization, and retrieval — the techniques that let you work with text far larger than any window.
Module 3: [LLM] Temperature & Sampling
LLM Course · Control how creative or how predictable a model is: temperature, top-p, top-k, and how to tune them for each task.
Lesson 6: Temperature Explained
What temperature actually does to the probability distribution, and when to use low, medium, or high values.
Lesson 7: Top-K & Top-P (Nucleus) Sampling
The other sampling dials: top-k trims the candidate list, top-p trims by probability mass. Learn to combine them.
Module 4: [LLM] Hallucinations
LLM Course · Why models confidently invent facts, the types of hallucinations, and the techniques to detect and reduce them.
Lesson 8: Why LLMs Hallucinate
Hallucinations are a feature of how LLMs work, not a bug you can switch off. Understand the root causes.
Lesson 9: Detecting & Reducing Hallucinations
Grounding, RAG, citations, self-checking prompts, and workflow design — the practical toolkit for trustworthy LLM output.
Module 5: [LLM] Agentic Loops & AI Agents
LLM Course · Move from single prompts to agents: the plan–act–observe loop, tools and function calling, and building your own agent.
Lesson 10: What Is an Agentic Loop?
One prompt = one answer. An agentic loop = the model plans, acts, observes, and repeats until the job is done.
Lesson 11: Tools & Function Calling
Tools are how agents touch the world. Learn function calling, tool schemas, and the ReAct pattern with a real example.
Lesson 12: Building a Simple Agent
Hands-on: assemble a minimal agent with tools, memory, and stop conditions — then meet the frameworks that do it for you.
Module 6: [LLM] Advanced LLM Topics
LLM Course · Level up with retrieval-augmented generation, embeddings & vector databases, and how to evaluate LLM systems.
Lesson 13: RAG — Retrieval-Augmented Generation
RAG grounds LLM answers in your own data: index, retrieve, augment, generate. The professional standard for trustworthy AI.
Lesson 14: Embeddings & Vector Databases
Embeddings turn text into coordinates where meaning = proximity. Learn similarity search and choosing a vector database.
Lesson 15: Evaluating LLM Systems
Benchmarks, metrics, and LLM-as-judge — how to measure quality, catch regressions, and know when your AI is good enough.
Module 7: [Prompt] Prompt Engineering Foundations
Prompt Engineering Course · Master the anatomy of an effective prompt and the three core techniques: zero-shot, few-shot, and chain-of-thought.
Lesson 16: The Anatomy of an Effective Prompt
Role, context, task, format, constraints — the five building blocks that turn vague requests into precise instructions.
Lesson 17: Zero-Shot, Few-Shot & Chain-of-Thought
The three core techniques every prompt engineer reaches for — and when to use each one.
Module 8: [Prompt] Advanced Prompting Patterns
Prompt Engineering Course · Structured outputs, reusable templates, and prompting for agents — the patterns professionals use in production.
Lesson 18: Structured Outputs & Reusable Templates
Force consistent, machine-readable outputs with JSON, tables, and XML tags — and stop rewriting prompts from scratch.
Lesson 19: Prompting for Agentic Workflows
System prompts for agents, tool-use instructions, prompt chaining, and evaluation — production prompting for AI tools.
Module 9: [Prompt] Advanced Reasoning & Techniques
Prompt Engineering Course · Go beyond the basics: self-consistency, tree of thought, persona prompting, and prompt chaining — with worked examples.
Lesson 20: Self-Consistency — Sample & Vote
Run the same prompt several times and take the majority answer to lift accuracy on hard reasoning tasks, with examples.
Lesson 21: Tree of Thought & Persona Prompting
Explore several reasoning branches before deciding, and assign the model a persona to unlock specialized perspectives — with examples.
Lesson 22: Prompt Chaining & Multi-Step Workflows
Break big tasks into focused prompts where each output feeds the next — with a full worked chain and validation checkpoints.
Module 10: [Prompt] Real-World Prompt Playbook
Prompt Engineering Course · Apply prompting where it pays: code generation, content writing, security against prompt injection, and evaluating prompts like an engineer.
Lesson 23: Prompting for Code Generation
The CODE framework, before/after examples, and the mistakes that make AI write broken code.
Lesson 24: Prompting for Writing & Content
The WRITE framework for audience, tone, and format — with before/after examples for posts, emails, and articles.
Lesson 25: Prompt Injection — Attacks & Defenses
How attackers smuggle instructions into your prompts, and the defensive patterns that keep AI tools safe — with examples.
Lesson 26: Evaluating & Iterating on Prompts
Golden sets, accuracy metrics, A/B testing prompt versions, and the iteration loop that turns prompting into engineering.