Skip to content
50% offFounding price until 1 DecemberSee prices
Square1 Ai
Get started
CoursesGenerative AI

Generative AI

beginner-advanced

Master LLMs, RAG, prompt engineering, and AI agents. Build real AI-powered products.

13 modules101 lessons10 projects
Take assessment

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.

What you'll learn

~150 h guided · about 30 weeks at 5 h/week · +138 h on projects

  • Explain why ChatGPT and Claude generate answers rather than looking them up like a search engine
  • Describe a program as ordinary text saved in a file and read by Python one line at a time
  • Define generative AI and distinguish it from discriminative AI
  • Explain temperature and its effect on output creativity
  • Write effective zero-shot prompts
  • Use the Anthropic Python and JavaScript SDKs
  • Generate text embeddings using embedding models
  • Define tools for an LLM to call

Curriculum

0/101 lessons
1

AI Foundations — optional basics (free)

Week 0 · 20 lessons

0/20
1

Beyond the chatbox: what AI assistants really are

2

How the model "thinks" — and why it changes how you ask

3

The capability map: what AI does brilliantly

4

The limits: hallucination, freshness, and what never to trust it with

5

Your first real win: turn a 30-minute task into 3

6

Context is everything: give it what it needs to know

7

Give it a role and a goal

8

Constraints and format: define what "good" looks like

9

Show, don't tell: examples and templates

10

Iterate like a pro: steer, don't restart

11

Documents and reports: summarise, extract, and draft better

12

Spreadsheets and data: Excel formulas, analysis, and charts

13

Presentations: from blank page to a solid deck

14

Long, messy input: transcripts, threads, notes, and screenshots

15

ChatGPT, Claude, Copilot, Gemini: which to reach for, and when

16

Make smarter decisions: AI as your thinking partner

17

Chaining steps: multi-part tasks done reliably

18

Your prompt library: reusable templates that save hours

19

Staying safe: privacy, accuracy, and company data

20

Capstone: do a real task end-to-end (graded) → your certificate

2

Module 0 — Foundations: How AI Works & the GenAI Toolkit

Week 0 · 23 lessons

0/23
1

What a program is and how to run your first one

2

Storing values in variables, and why text and numbers behave differently

3

Making decisions with if, else and comparisons

4

Storing many values in a list

5

Looking things up by name with dictionaries

6

Doing something to every item with loops

7

Writing your own functions

8

Reading errors without panic

9

Finding the mistake in your own code

10

Saving your code in a file and running it

11

Importing code other people have written

12

Giving each project its own environment

13

Talking to your computer with the terminal

14

Saving your work with Git

15

Putting your work on GitHub

16

What an array is, and why a list is not enough

17

Picking out pieces: indexing and slicing, including two dimensions

18

Maths on a whole array at once, and where you go next

19

How Machine Learning Works: A GenAI Primer

20

Vectors, Embeddings & Similarity

21

Tokens, Probability & How LLMs Generate Text

22

Python for GenAI

23

Git & the GenAI Toolkit

3

Foundations of Generative AI

Week 1 · 5 lessons

0/5
1

What is Generative AI?

2

How Transformers Work

3

Tokens, Embeddings & Context

4

The LLM Landscape

5

Your First AI Application

4

Large Language Models Deep Dive

Week 2 · 5 lessons

0/5
1

Temperature, Top-p & Sampling

2

Context Windows & Memory

3

Model Capabilities & Benchmarks

4

Multimodal AI: Beyond Text

5

AI Safety & Alignment Basics

5

Prompt Engineering Mastery

Week 3 · 5 lessons

0/5
1

Zero-shot & Few-shot Prompting

2

Chain-of-Thought Prompting

3

System Prompts & Personas

4

Structured Output & JSON Mode

5

Advanced Prompt Patterns

6

Building with LLM APIs

Week 4 · 5 lessons

0/5
1

Anthropic SDK Deep Dive

2

Streaming & Real-time Responses

3

Cost Optimisation Strategies

4

Building a Chat Application

5

Rate Limits & Production Patterns

7

Retrieval-Augmented Generation (RAG)

Week 5 · 5 lessons

0/5
1

Embeddings & Vector Search

2

Document Chunking Strategies

3

Building a RAG Pipeline

4

Advanced RAG Techniques

5

RAG Evaluation & Optimisation

8

AI Agents & Tool Use

Week 6 · 5 lessons

0/5
1

Function Calling & Tool Use

2

Building an AI Agent Loop

3

Agent Memory Systems

4

Multi-Agent Systems

5

Autonomous AI Workflows

9

Fine-tuning & Embeddings

Week 7 · 5 lessons

0/5
1

When to Fine-tune vs Prompt

2

Dataset Preparation

3

Fine-tuning with OpenAI API

4

Embedding Models & Semantic Search

5

LoRA & Parameter-Efficient Tuning

10

Production AI Systems

Week 8 · 5 lessons

0/5
1

Evaluation & Testing AI Systems

2

Observability & Monitoring

3

Safety & Guardrails

4

Latency & Cost Optimisation

5

Deploying AI Applications

11

Context Engineering

Week 9 · 6 lessons

0/6
1

Context as a Budget

2

Retrieval vs. Context (RAG vs Long-Context)

3

Compaction & Summarization

4

Structured Long-Term Memory

5

Cache-Aware Context Construction

6

Long-Context Evaluation

12

Modern LLM Architectures

Week 10 · 6 lessons

0/6
1

Mixture of Experts (MoE): Sparse Scaling

2

Efficient Attention: FlashAttention, GQA/MQA & Latent Attention

3

Long-Context Architecture: RoPE, YaRN & Position Scaling

4

Reasoning Models & Test-Time Compute

5

DeepSeek & the Open Efficiency Frontier

6

Small Models & the Distillation Frontier

13

Voice & Multimodal Agents

Week 11 · 6 lessons

0/6
1

Beyond Text: The Multimodal Model Landscape

2

Vision in Practice: Documents, Screens and Photos

3

Speech In: Transcription and Understanding

4

Speech Out: TTS and Voice Design

5

Realtime Voice Agents

6

Multimodal Pipelines in Production

Advanced tier

Advanced Generative AI

6 senior modules · 30lessons · capstone & certificate. Upgrade your plan to unlock the advanced tier.

Advanced RAG & Retrieval at Scale

5 lessons

1

Beyond Naive RAG: Failure Modes & the Retrieval Stack

2

Hybrid Search: Dense + Sparse (BM25) & Fusion

3

Re-ranking with Cross-Encoders

4

Query Transformation: HyDE, Multi-Query, Decomposition & Routing

5

Production RAG: Indexing at Scale, Caching & Evaluation-Driven Iteration

Agentic Systems & Orchestration

5 lessons

1

Agent Architectures: ReAct, Plan-and-Execute & Reflexion

2

Tool Use & Function Calling at Depth

3

Memory & State: Short-term, Long-term, Episodic & Semantic

4

Multi-Agent Orchestration: Supervisor, Hand-offs & Shared State

5

Reliability: Loops, Budgets, Guardrails & Failure Recovery

Fine-tuning & Model Adaptation

5 lessons

1

The Adaptation Spectrum: Prompt → RAG → SFT → Preference Tuning

2

Supervised Fine-tuning (SFT): Data, Formatting & Training Dynamics

3

Parameter-Efficient Tuning: LoRA, QLoRA & Adapters

4

Preference Optimisation: RLHF & DPO

5

Evaluating, Merging & Serving Fine-tuned Models

Evaluation, Observability & LLMOps

5 lessons

1

Evaluating LLM Systems: Metrics, Rubrics & the Eval Pyramid

2

LLM-as-Judge: Designing, Calibrating & De-biasing

3

Offline Eval Harnesses & Regression Gates in CI

4

Observability & Tracing in Production

5

Online Experimentation: A/B Tests, Canaries & Versioning

Safety, Alignment & Red-teaming

5 lessons

1

The LLM Threat Model: Prompt Injection & Jailbreaks

2

Guardrails: Input/Output Filtering, Schema & Policy Enforcement

3

Red-teaming LLM Applications

4

Data Privacy, PII & Compliance in LLM Apps

5

Alignment Foundations: RLHF, Constitutional AI & Their Limits

Efficient Inference & Serving

5 lessons

1

The Cost & Latency Model of Transformer Inference

2

Quantization: INT8/INT4, GPTQ, AWQ & Trade-offs

3

KV-Cache, Continuous Batching & PagedAttention

4

Speculative Decoding, Distillation & Smaller Models

5

Serving Architecture: Routing, Caching, Autoscaling & SLOs

What you'll build

10 projects · ~138 h · each graded against a rubric

  1. AI-Powered Chatbot

    beginner · ~8 h

    Python or JavaScriptAnthropic SDKNext.js or Flask

  2. Smart Document Q&A (RAG)

    beginner · ~10 h

    PythonAnthropic SDKpgvector or ChromaNext.js

  3. Prompt Engineering Toolkit

    beginner · ~6 h

    Next.jsAnthropic SDKSupabase

  4. AI Code Review Assistant

    intermediate · ~12 h

    Next.jsAnthropic SDKMonaco EditorSupabase

  5. AI Research Agent

    intermediate · ~15 h

    PythonAnthropic SDKTavily or SerpAPILangChain (optional)

  6. Personalised Learning Assistant

    intermediate · ~14 h

    Next.jsAnthropic SDKSupabase

  7. RAG-Powered Knowledge Base

    intermediate · ~16 h

    Next.jsSupabase + pgvectorAnthropic SDKPDF/DOCX parser

  8. AI Content Generation Platform

    intermediate · ~12 h

    Next.jsAnthropic SDKSupabaseVercel

  9. AI-Powered SaaS Starter

    advanced · ~25 h

    Next.jsSupabaseAnthropic SDKStripe

  10. Multi-Agent AI System

    advanced · ~20 h

    PythonAnthropic SDKRedis or SupabaseFastAPI

What we track

Everything below is graded by Nova and kept on your record: the thing an employer can open, run and verify.

Get started

Take the free assessment to see your skill level and get a personalised learning plan.

Take assessment

Featured projects

AI-Powered Chatbot

Python or JavaScriptAnthropic SDK

Smart Document Q&A (RAG)

PythonAnthropic SDK

Prompt Engineering Toolkit

Next.jsAnthropic SDK

About

13 modules, 101 lessons
~150 hours of guided learning
10 portfolio projects (~138h)
AI-graded exercises

Generative AI

20 questions · ~30 minutes

Take the assessment →

The people behind this track

Nova grades every submission; these are the humans who wrote the brief and stand behind it.

Nikhil De Silva

Founder, Square1 Ai

Built Square1 Ai to close the gap between knowing and doing: every lesson ends in work that gets graded, and every student has someone in their corner.