Master LLMs, RAG, prompt engineering, and AI agents. Build real AI-powered products.
Never written code? You can still start here.
Module 0 opens with 18 lessons of programming from nothing — your first program, variables, loops, functions, reading errors, the terminal, Git and arrays — before any of the Generative AI material. No prior coding assumed.
AI Foundations — optional basics (free)
Week 0 · 20 lessons
Beyond the chatbox: what AI assistants really are
How the model "thinks" — and why it changes how you ask
The capability map: what AI does brilliantly
The limits: hallucination, freshness, and what never to trust it with
Your first real win: turn a 30-minute task into 3
6 senior modules · 30lessons · capstone & certificate. Upgrade your plan to unlock the advanced tier.
Advanced RAG & Retrieval at Scale
5 lessons
Beyond Naive RAG: Failure Modes & the Retrieval Stack
Hybrid Search: Dense + Sparse (BM25) & Fusion
Get started
Take the free assessment to see your skill level and get a personalised learning plan.
Take AssessmentFeatured Projects
AI-Powered Chatbot
Smart Document Q&A (RAG)
Prompt Engineering Toolkit
About
Generative AI
20 questions · ~30 minutes
Context is everything: give it what it needs to know
Give it a role and a goal
Constraints and format: define what "good" looks like
Show, don't tell: examples and templates
Iterate like a pro: steer, don't restart
Documents and reports: summarise, extract, and draft better
Spreadsheets and data: Excel formulas, analysis, and charts
Presentations: from blank page to a solid deck
Long, messy input: transcripts, threads, notes, and screenshots
ChatGPT, Claude, Copilot, Gemini: which to reach for, and when
Make smarter decisions: AI as your thinking partner
Chaining steps: multi-part tasks done reliably
Your prompt library: reusable templates that save hours
Staying safe: privacy, accuracy, and company data
Capstone: do a real task end-to-end (graded) → your certificate
Module 0 — Foundations: How AI Works & the GenAI Toolkit
Week 0 · 23 lessons
What a program is and how to run your first one
Storing values in variables, and why text and numbers behave differently
Making decisions with if, else and comparisons
Storing many values in a list
Looking things up by name with dictionaries
Doing something to every item with loops
Writing your own functions
Reading errors without panic
Finding the mistake in your own code
Saving your code in a file and running it
Importing code other people have written
Giving each project its own environment
Talking to your computer with the terminal
Saving your work with Git
Putting your work on GitHub
What an array is, and why a list is not enough
Picking out pieces: indexing and slicing, including two dimensions
Maths on a whole array at once, and where you go next
How Machine Learning Works: A GenAI Primer
Vectors, Embeddings & Similarity
Tokens, Probability & How LLMs Generate Text
Python for GenAI
Git & the GenAI Toolkit
Foundations of Generative AI
Week 1 · 5 lessons
What is Generative AI?
How Transformers Work
Tokens, Embeddings & Context
The LLM Landscape
Your First AI Application
Large Language Models Deep Dive
Week 2 · 5 lessons
Temperature, Top-p & Sampling
Context Windows & Memory
Model Capabilities & Benchmarks
Multimodal AI: Beyond Text
AI Safety & Alignment Basics
Prompt Engineering Mastery
Week 3 · 5 lessons
Zero-shot & Few-shot Prompting
Chain-of-Thought Prompting
System Prompts & Personas
Structured Output & JSON Mode
Advanced Prompt Patterns
Building with LLM APIs
Week 4 · 5 lessons
Anthropic SDK Deep Dive
Streaming & Real-time Responses
Cost Optimisation Strategies
Building a Chat Application
Rate Limits & Production Patterns
Retrieval-Augmented Generation (RAG)
Week 5 · 5 lessons
Embeddings & Vector Search
Document Chunking Strategies
Building a RAG Pipeline
Advanced RAG Techniques
RAG Evaluation & Optimisation
AI Agents & Tool Use
Week 6 · 5 lessons
Function Calling & Tool Use
Building an AI Agent Loop
Agent Memory Systems
Multi-Agent Systems
Autonomous AI Workflows
Fine-tuning & Embeddings
Week 7 · 5 lessons
When to Fine-tune vs Prompt
Dataset Preparation
Fine-tuning with OpenAI API
Embedding Models & Semantic Search
LoRA & Parameter-Efficient Tuning
Production AI Systems
Week 8 · 5 lessons
Evaluation & Testing AI Systems
Observability & Monitoring
Safety & Guardrails
Latency & Cost Optimisation
Deploying AI Applications
Context Engineering
Week 9 · 6 lessons
Context as a Budget
Retrieval vs. Context (RAG vs Long-Context)
Compaction & Summarization
Structured Long-Term Memory
Cache-Aware Context Construction
Long-Context Evaluation
Modern LLM Architectures
Week 10 · 6 lessons
Mixture of Experts (MoE): Sparse Scaling
Efficient Attention: FlashAttention, GQA/MQA & Latent Attention
Long-Context Architecture: RoPE, YaRN & Position Scaling
Reasoning Models & Test-Time Compute
DeepSeek & the Open Efficiency Frontier
Small Models & the Distillation Frontier
Voice & Multimodal Agents
Week 11 · 6 lessons
Beyond Text: The Multimodal Model Landscape
Vision in Practice: Documents, Screens and Photos
Speech In: Transcription and Understanding
Speech Out: TTS and Voice Design
Realtime Voice Agents
Multimodal Pipelines in Production
Re-ranking with Cross-Encoders
Query Transformation: HyDE, Multi-Query, Decomposition & Routing
Production RAG: Indexing at Scale, Caching & Evaluation-Driven Iteration
Agentic Systems & Orchestration
5 lessons
Agent Architectures: ReAct, Plan-and-Execute & Reflexion
Tool Use & Function Calling at Depth
Memory & State: Short-term, Long-term, Episodic & Semantic
Multi-Agent Orchestration: Supervisor, Hand-offs & Shared State
Reliability: Loops, Budgets, Guardrails & Failure Recovery
Fine-tuning & Model Adaptation
5 lessons
The Adaptation Spectrum: Prompt → RAG → SFT → Preference Tuning
Supervised Fine-tuning (SFT): Data, Formatting & Training Dynamics
Parameter-Efficient Tuning: LoRA, QLoRA & Adapters
Preference Optimisation: RLHF & DPO
Evaluating, Merging & Serving Fine-tuned Models
Evaluation, Observability & LLMOps
5 lessons
Evaluating LLM Systems: Metrics, Rubrics & the Eval Pyramid
LLM-as-Judge: Designing, Calibrating & De-biasing
Offline Eval Harnesses & Regression Gates in CI
Observability & Tracing in Production
Online Experimentation: A/B Tests, Canaries & Versioning
Safety, Alignment & Red-teaming
5 lessons
The LLM Threat Model: Prompt Injection & Jailbreaks
Guardrails: Input/Output Filtering, Schema & Policy Enforcement
Red-teaming LLM Applications
Data Privacy, PII & Compliance in LLM Apps
Alignment Foundations: RLHF, Constitutional AI & Their Limits
Efficient Inference & Serving
5 lessons
The Cost & Latency Model of Transformer Inference
Quantization: INT8/INT4, GPTQ, AWQ & Trade-offs
KV-Cache, Continuous Batching & PagedAttention
Speculative Decoding, Distillation & Smaller Models
Serving Architecture: Routing, Caching, Autoscaling & SLOs