Explore the Complete Generative AI Course
Pillar 1: AI Foundations & Mental Models
-
AI is already around you
Meet AI through small, familiar tasks.
8 interactive activities · ~37 mins → -
Your first safe conversation
Build a useful invitation, one choice at a time.
8 interactive activities · ~28 mins → -
Useful help, sensible limits
Choose useful assistance and check what matters.
8 interactive activities · ~30 mins → -
Learning from examples
Follow data to model to output, with no mathematics.
10 interactive activities · ~46 mins → -
How an answer is made
Why answers vary, and why plausible details can be invented.
7 interactive activities · ~31 mins → -
What the app can actually see
Inspect what a particular interaction really has available.
9 interactive activities · ~42 mins → -
Give a useful brief
Supply what a task needs, without relying on prompt tricks.
8 interactive activities · ~36 mins → -
Improve one thing at a time
Diagnose a disappointing result and revise it on purpose.
7 interactive activities · ~31 mins → -
Work from material you provide
Transform a source while preserving its meaning and limits.
9 interactive activities · ~41 mins → -
Check an answer
Use evidence to accept, correct or hold each claim.
8 interactive activities · ~36 mins → -
Protect people and information
Decide what to send, and what to do if too much went out.
8 interactive activities · ~37 mins → -
Images, voices and trust
Judge generated media, and refuse to be hurried.
9 interactive activities · ~40 mins → -
Learn with AI
Keep the thinking and the recall with the learner.
7 interactive activities · ~30 mins → -
Write and create with AI
Produce original work that still sounds like you.
7 interactive activities · ~30 mins → -
Plan and decide with AI
Treat a generated plan as a draft to be made workable.
8 interactive activities · ~37 mins → -
Tools and agents
Tell a suggestion from an action, and supervise the difference.
8 interactive activities · ~38 mins → -
AI, people and society
See the human choices behind a system's behaviour.
8 interactive activities · ~38 mins → -
Your everyday AI toolkit
Build a routine you will still follow when busy.
8 interactive activities · ~39 mins →
Pillar 2: Prompt Architecture & Interaction
-
Files and Markdown without mystery
Read and edit the small text files agents work from.
8 interactive activities · ~36 mins → -
Configuration is data with a format
Read small configuration files and keep credentials out of them.
10 interactive activities · ~49 mins → -
Different jobs for different models
Describe a model by the job it does, not by its design.
9 interactive activities · ~38 mins → -
Different ways to learn
Find where a training setup's signal comes from.
10 interactive activities · ~43 mins → -
The examples shape the model
Inspect a collection for the faults that matter.
10 interactive activities · ~43 mins → -
Use it: choose a model for the job
Turn three chapters of theory into one defensible decision.
7 interactive activities · ~34 mins → -
A neural network, one small part at a time
Trace a numerical model through connected layers.
9 interactive activities · ~42 mins → -
One training step at a time
Predict, measure, adjust — and which numbers are which.
10 interactive activities · ~46 mins → -
Learning that works on new examples
Judge generalisation with separate evidence.
10 interactive activities · ~47 mins → -
Use it: read a model card and find the gap
Find the absence that would change your decision.
7 interactive activities · ~35 mins → -
From text to small pieces
Tokens, identifiers, and what a budget is counted in.
7 interactive activities · ~30 mins → -
Representing relationships with numbers
Learned rows, similarity, shares and weighted mixing.
10 interactive activities · ~46 mins → -
The problem attention helps solve
Order, distance, and the fixed-summary bottleneck.
8 interactive activities · ~35 mins → -
Use it: budget a long document
Fit a long source into a small window, honestly.
7 interactive activities · ~34 mins → -
Attention: match, weight and mix
Query, key, value, scores, shares, and the weighted mixture.
10 interactive activities · ~43 mins → -
Attention across a sequence
Self and cross attention, order signals, masking, many heads.
9 interactive activities · ~39 mins → -
Build the Transformer picture
The block, the stack, and what 2017 actually contributed.
10 interactive activities · ~43 mins → -
Use it: diagnose a lost detail
Why a supplied fact went missing, and what to do about it.
7 interactive activities · ~35 mins → -
Language models have different designs
Encoder, decoder, encoder-decoder, embeddings, and the alternatives.
8 interactive activities · ~37 mins → -
Seeing, hearing and combining media
Pixels, patches, sound over time, and reading a capability card.
9 interactive activities · ~42 mins → -
Different ways to generate media
Denoising, latents, adversarial training and learned paths.
9 interactive activities · ~39 mins → -
Use it: choose a media capability
Direction, capability table, route, and a written disqualifier.
7 interactive activities · ~34 mins →
Pillar 3: Tools, Workflows & Agents
-
From a base model to a useful assistant
Pretraining, fine-tuning, demonstrations, and where a change lives.
9 interactive activities · ~38 mins → -
Learning from feedback
Preferences, reward models, RLHF, DPO, and reward gaming.
9 interactive activities · ~40 mins → -
Why models become more capable
Data, capacity, compute, synthetic examples and answer-time work.
9 interactive activities · ~39 mins → -
Use it: judge a model release claim
The claim, the mechanism, the missing baseline, a fair line.
7 interactive activities · ~34 mins → -
Give a model useful outside information
Finding, chunking, ranking, grounding, freshness and permission.
9 interactive activities · ~38 mins → -
What happens while an answer is generated
Distributions, greedy, sampling, temperature, top-p, caching.
9 interactive activities · ~38 mins → -
Useful models can be smaller and simpler
Linear models, trees, ensembles, routing, distillation, precision.
9 interactive activities · ~40 mins → -
Use it: fix a wrong answer three ways
Classify the failure, repair in the right layer, attribute the fix.
8 interactive activities · ~37 mins → -
What does better actually mean?
Criteria, precision, recall, thresholds, subgroups and sample size.
9 interactive activities · ~41 mins → -
Test reliability beyond a headline score
Fair conditions, contamination, robustness, calibration, judges.
8 interactive activities · ~34 mins → -
Choose, monitor and keep learning
Model cards, licences, deployment routes, updates and monitoring.
8 interactive activities · ~35 mins → -
Use it: run a fair comparison
One task, one criterion, conditions held, and an honest limit.
7 interactive activities · ~32 mins → -
From hidden states to an answer
Vocabulary, scores, the output head, targets and stop reasons.
8 interactive activities · ~35 mins → -
What is actually in a conversation
Roles, precedence, templates, assembly, compaction and memory.
8 interactive activities · ~35 mins → -
Why responses take time and cost money
Prefill, decode, caches, memory limits and end-to-end budgets.
8 interactive activities · ~34 mins → -
Reasoning and adaptation after initial training
Few-shot, written steps, self-consistency, further training, unlearning.
7 interactive activities · ~28 mins → -
Use it: read your own request receipt
Split the time, attribute the cost, find the reuse, total the task.
7 interactive activities · ~34 mins → -
A workspace and its change history
Folders, repositories, diffs, commits, worktrees and publication.
8 interactive activities · ~35 mins → -
From a request to a tool result
APIs, tools, schemas, proposals, results and failure classes.
8 interactive activities · ~32 mins → -
The software around the model
The harness, workflows, plans, context selection, state and stops.
7 interactive activities · ~29 mins → -
Reliable actions over several steps
Retries, idempotency, permissions, sandboxes, handoffs, checkpoints.
9 interactive activities · ~39 mins → -
Which instruction file does what?
READMEs, agent guidance, scope, saved notes and what enforces nothing.
8 interactive activities · ~34 mins → -
A skill packages reusable know-how
Triggers, entrypoints, staged loading, resources and a small evaluation.
8 interactive activities · ~33 mins → -
Hooks, plugins and reusable systems
Events, scripts, packages, provenance, dependencies and versions.
8 interactive activities · ~33 mins →
Pillar 4: Judgment, Verification & Safety
-
MCP connects an application to capabilities
Host, client, server, messages, versions and mutual support.
9 interactive activities · ~40 mins → -
Tools, resources and prompts
Operations, addresses, templates, prepared workflows and errors.
8 interactive activities · ~32 mins → -
Transport and authorized access
Local processes, endpoints, streaming, scopes, tokens and revocation.
9 interactive activities · ~39 mins → -
MCP and its neighboring ideas
APIs, tool calling, skills, retrieval, agent delegation and packages.
7 interactive activities · ~29 mins → -
Inspect, connect and troubleshoot
Narrow scope, provenance, manual inspection, selection and layers.
7 interactive activities · ~29 mins → -
Advanced MCP features and version changes
Progress, cancellation, input requests, interfaces, long tasks, eras.
9 interactive activities · ~40 mins → -
Brief a coding task
Observed problems, acceptance criteria, scope, exploration, reproducers and right-sized plans.
8 interactive activities · ~42 mins → -
Check the work an agent returns
Diffs, matching a check to the risk, regression tests, failure output and shared blind spots.
7 interactive activities · ~38 mins → -
Keep work recoverable and shareable
Checkpoints, worktrees, conflicts, handoff notes, pull requests and release verification.
8 interactive activities · ~44 mins → -
Meet Claude Code and start a session
Model against agent program, surfaces and execution location, setup stages, the right checkout and the first prompt.
7 interactive activities · ~36 mins → -
Guide Claude Code with context and extensions
Project guidance, diagnosing a rule that did not apply, skills, narrow connections, delegation and hooks.
7 interactive activities · ~39 mins → -
Claude Code use cases and recovery
Exploring a path, repairing a bug, narrow tests, refactors, documentation from real code, and stalled sessions.
8 interactive activities · ~44 mins → -
Meet Codex and choose a workspace
Product against model, surfaces, local and cloud state, access stages, the starting state and a first read.
7 interactive activities · ~38 mins → -
Guide Codex and inspect its reach
AGENTS.md discovery, overrides, skills, connected servers, the three permission dials and surviving compaction.
7 interactive activities · ~36 mins → -
Codex use cases and handoffs
Scoped changes, evidenced diagnosis, review against a contract, delegation, reports, and an honest close.
8 interactive activities · ~43 mins → -
Editor and cloud coding agents
Pending changes, assistance modes, briefs for detached runs, review surfaces and choosing by review fit.
7 interactive activities · ~38 mins → -
Other coding agents and interfaces
Terminal, editor and cloud examples, open clients with configured providers, explicit file context and frameworks.
7 interactive activities · ~36 mins → -
Start one small task in another tool
The same four checks in five unfamiliar products, and what makes a comparison between them fair.
7 interactive activities · ~36 mins → -
Useful agent work beyond a demo
Research briefs, data cleanup, rendered documents, live interfaces, automation limits and the simplest adequate system.
8 interactive activities · ~43 mins →