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.
Taught by Amol Shukla
- Modules
- 10
- Lessons
- 26
- Level
- Beginner
- Rating
- 4.9 / 5
Syllabus
10 modules · 26 lessons01Module 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.
3 lessons
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.
- 1.1Lesson 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.40 mins
- 1.2Lesson 2: The Transformer & Self-AttentionPeek inside the model: embeddings, the transformer stack, and the self-attention mechanism that decides which words matter.55 mins
- 1.3Lesson 3: The Training Pipeline — Pre-training, Fine-tuning & RLHFHow a raw neural network becomes ChatGPT: pre-training on trillions of tokens, supervised fine-tuning, and reinforcement learning from human feedback.60 mins
02Module 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.
2 lessons
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.
- 2.1Lesson 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.45 mins
- 2.2Lesson 5: Managing Long ContextsChunking, sliding windows, summarization, and retrieval — the techniques that let you work with text far larger than any window.55 mins
03Module 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.
2 lessons
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.
- 3.1Lesson 6: Temperature ExplainedWhat temperature actually does to the probability distribution, and when to use low, medium, or high values.45 mins
- 3.2Lesson 7: Top-K & Top-P (Nucleus) SamplingThe other sampling dials: top-k trims the candidate list, top-p trims by probability mass. Learn to combine them.45 mins
04Module 4: [LLM] Hallucinations
LLM Course · Why models confidently invent facts, the types of hallucinations, and the techniques to detect and reduce them.
2 lessons
Module 4: [LLM] Hallucinations
LLM Course · Why models confidently invent facts, the types of hallucinations, and the techniques to detect and reduce them.
- 4.1Lesson 8: Why LLMs HallucinateHallucinations are a feature of how LLMs work, not a bug you can switch off. Understand the root causes.45 mins
- 4.2Lesson 9: Detecting & Reducing HallucinationsGrounding, RAG, citations, self-checking prompts, and workflow design — the practical toolkit for trustworthy LLM output.55 mins
05Module 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.
3 lessons
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.
- 5.1Lesson 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.50 mins
- 5.2Lesson 11: Tools & Function CallingTools are how agents touch the world. Learn function calling, tool schemas, and the ReAct pattern with a real example.60 mins
- 5.3Lesson 12: Building a Simple AgentHands-on: assemble a minimal agent with tools, memory, and stop conditions — then meet the frameworks that do it for you.75 mins
06Module 6: [LLM] Advanced LLM Topics
LLM Course · Level up with retrieval-augmented generation, embeddings & vector databases, and how to evaluate LLM systems.
3 lessons
Module 6: [LLM] Advanced LLM Topics
LLM Course · Level up with retrieval-augmented generation, embeddings & vector databases, and how to evaluate LLM systems.
- 6.1Lesson 13: RAG — Retrieval-Augmented GenerationRAG grounds LLM answers in your own data: index, retrieve, augment, generate. The professional standard for trustworthy AI.60 mins
- 6.2Lesson 14: Embeddings & Vector DatabasesEmbeddings turn text into coordinates where meaning = proximity. Learn similarity search and choosing a vector database.55 mins
- 6.3Lesson 15: Evaluating LLM SystemsBenchmarks, metrics, and LLM-as-judge — how to measure quality, catch regressions, and know when your AI is good enough.60 mins
07Module 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.
2 lessons
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.
- 7.1Lesson 16: The Anatomy of an Effective PromptRole, context, task, format, constraints — the five building blocks that turn vague requests into precise instructions.45 mins
- 7.2Lesson 17: Zero-Shot, Few-Shot & Chain-of-ThoughtThe three core techniques every prompt engineer reaches for — and when to use each one.50 mins
08Module 8: [Prompt] Advanced Prompting Patterns
Prompt Engineering Course · Structured outputs, reusable templates, and prompting for agents — the patterns professionals use in production.
2 lessons
Module 8: [Prompt] Advanced Prompting Patterns
Prompt Engineering Course · Structured outputs, reusable templates, and prompting for agents — the patterns professionals use in production.
- 8.1Lesson 18: Structured Outputs & Reusable TemplatesForce consistent, machine-readable outputs with JSON, tables, and XML tags — and stop rewriting prompts from scratch.50 mins
- 8.2Lesson 19: Prompting for Agentic WorkflowsSystem prompts for agents, tool-use instructions, prompt chaining, and evaluation — production prompting for AI tools.60 mins
09Module 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.
3 lessons
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.
- 9.1Lesson 20: Self-Consistency — Sample & VoteRun the same prompt several times and take the majority answer to lift accuracy on hard reasoning tasks, with examples.45 mins
- 9.2Lesson 21: Tree of Thought & Persona PromptingExplore several reasoning branches before deciding, and assign the model a persona to unlock specialized perspectives — with examples.50 mins
- 9.3Lesson 22: Prompt Chaining & Multi-Step WorkflowsBreak big tasks into focused prompts where each output feeds the next — with a full worked chain and validation checkpoints.55 mins
10Module 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.
4 lessons
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.
- 10.1Lesson 23: Prompting for Code GenerationThe CODE framework, before/after examples, and the mistakes that make AI write broken code.55 mins
- 10.2Lesson 24: Prompting for Writing & ContentThe WRITE framework for audience, tone, and format — with before/after examples for posts, emails, and articles.50 mins
- 10.3Lesson 25: Prompt Injection — Attacks & DefensesHow attackers smuggle instructions into your prompts, and the defensive patterns that keep AI tools safe — with examples.55 mins
- 10.4Lesson 26: Evaluating & Iterating on PromptsGolden sets, accuracy metrics, A/B testing prompt versions, and the iteration loop that turns prompting into engineering.55 mins