Intro
Start here
Start with Foundations
No technical experience required. Build your understanding from the ground up.
No technical experience required. Build your understanding from the ground up.
3h
Start here
Course overview
AI Agents
Design agent systems with explicit tools, memory, approvals, evaluation, and security controls you can defend in real work.
Start at the top, move stage by stage, then use practice and stage tests when you want a stronger check.
Stage 1 of 6
Foundations
No technical experience required. Build your understanding from the ground up.
No technical experience required. Build your understanding from the ground up.
M01
Module 1
Understanding AI
Let me start with what AI is not.
Artificial Intelligence.
Not started
35 min
Open module
M02
Module 2
From LLMs to agents
A Large Language Model (LLM) is like an incredibly well-read assistant who has consumed most of human knowledge available on the internet.
Key LLM characteristics Stateless .
Not started
35 min
Open module
M03
Module 3
Your computer's command line
I know the command line can look intimidating.
Everyone who is good at the command line was once staring at a blank terminal wondering what to type.
Not started
35 min
Open module
M04
Module 4
Setting up your environment
Python is the language of AI development.
A virtual environment is an isolated space for your project's dependencies.
Not started
35 min
Open module
M05
Module 5
Your first AI interaction
Let us have your first conversation with a local AI model.
Now let us write a Python script that talks to Ollama.
Not started
35 min
Open module
Practice
Practice test
Foundations practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 10 published questions.
Self-paced
Open practice
Test
Stage test
Foundations stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 10 questions, 70% pass mark.
15 min
Open stage test
Stage 2 of 6
Core concepts
Build deep understanding of how AI agents work under the hood.
Build deep understanding of how AI agents work under the hood.
Intro
Start here
Start with Core concepts
Build deep understanding of how AI agents work under the hood.
Build deep understanding of how AI agents work under the hood.
4h
Start here
M01
Module 1
How AI agents think
ReAct stands for reasoning and acting .
The three steps Thought .
Not started
45 min
Open module
M02
Module 2
Tools and actions
Tools are functions that agents can call to interact with the world.
Tool.
Not started
45 min
Open module
M03
Module 3
Memory and context
Short-Term Memory.
Long-Term Memory.
Not started
45 min
Open module
M04
Module 4
Design patterns
For complex tasks, planning before acting often works better than interleaved reasoning.
The agent reviews and improves its own output before presenting it.
Not started
45 min
Open module
M05
Module 5
Architecture fundamentals
State is everything your agent needs to remember to complete its task.
""" Agent State Management ====================== Immutable state for reliable agent operation.
Not started
45 min
Open module
Practice
Practice test
Core concepts practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 10 published questions.
Self-paced
Open practice
Test
Stage test
Core concepts stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 10 questions, 70% pass mark.
15 min
Open stage test
Stage 3 of 6
Practical building
Hands-on implementation of real-world agent systems.
Hands-on implementation of real-world agent systems.
Intro
Start here
Start with Practical building
Hands-on implementation of real-world agent systems.
Hands-on implementation of real-world agent systems.
5h
Start here
M01
Module 1
Building your first agent
Let us build a production-ready single agent step by step.
Now let us create some useful tools for our agent.
Not started
1h
Open module
M02
Module 2
Multi-agent systems
In practice, when tasks cross more than a couple of domains, a single agent often degrades quickly.
A central supervisor routes requests to specialised sub-agents.
Not started
1h
Open module
M03
Module 3
Workflow automation with n8n
n8n (pronounced "n-eight-n") is a workflow automation platform that lets you connect different apps and services.
Using Docker (Recommended): # macOS / Linux docker run -it --rm --name n8n \ -p 5678:5678 \ -v n8n_data:/home/node/.n8n \ n8nio/n8n # Windows PowerShell docker run -it --rm --name n8n ` -p 5678:5678.
Not started
1h
Open module
M04
Module 4
Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open protocol for connecting AI clients to external tools and data sources.
Before MCP .
Not started
1h
Open module
M05
Module 5
Integration and APIs
Computer use is moving from demo territory into real workflows, but the safe lesson is not which model tops which benchmark.
Computer use is impressive but not magic.
Not started
1h
Open module
Practice
Practice test
Practical building practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 12 published questions.
Self-paced
Open practice
Test
Stage test
Practical building stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 12 questions, 70% pass mark.
20 min
Open stage test
Stage 4 of 6
Security and ethics
Critical understanding of AI security threats and responsible deployment.
Critical understanding of AI security threats and responsible deployment.
Intro
Start here
Start with Security and ethics
Critical understanding of AI security threats and responsible deployment.
Critical understanding of AI security threats and responsible deployment.
2h
Start here
M01
Module 1
The threat landscape
AI agents face unique security challenges that traditional software does not.
OWASP maintains a widely used list of risks and mitigations for LLM and generative AI applications.
Not started
40 min
Open module
M02
Module 2
Secure implementation
Every piece of data that enters your agent system is a potential attack vector.
Input Validation.
Not started
40 min
Open module
M03
Module 3
Ethics and responsible AI
AI agents inherit biases from their training data, their developers, and their deployment context.
AI Bias.
Not started
40 min
Open module
Practice
Practice test
Security and ethics practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 9 published questions.
Self-paced
Open practice
Test
Stage test
Security and ethics stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 9 questions, 70% pass mark.
15 min
Open stage test
Stage 5 of 6
Advanced mastery
Expert-level techniques for production AI systems.
Expert-level techniques for production AI systems.
Intro
Start here
Start with Advanced mastery
Expert-level techniques for production AI systems.
Expert-level techniques for production AI systems.
4h
Start here
M01
Module 1
Fine-tuning open source models
My opinion is that fine tuning is only worth it when you can name the win you want, the risk you accept, and the test you will run before anyone depends on it.
Fine-tuning is not always the answer.
Not started
1h
Open module
M02
Module 2
Enterprise architectures
Enterprise architecture is where good agent ideas get messy.
When building agents for multiple customers, data isolation is critical.
Not started
1h
Open module
M03
Module 3
Production deployment
Production is not just running code.
# Dockerfile for AI Agent FROM python:3.12-slim # Set working directory WORKDIR /app # Install system dependencies RUN apt-get update && apt-get install -y --no-install-recommends \ curl \.
Not started
1h
Open module
M04
Module 4
Research frontiers
This module is about judgement.
The research landscape is shifting fast.
Not started
1h
Open module
Practice
Practice test
Advanced mastery practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 8 published questions.
Self-paced
Open practice
Test
Stage test
Advanced mastery stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 8 questions, 70% pass mark.
15 min
Open stage test
Stage 6 of 6
Capstone and certification
Demonstrate mastery through a comprehensive project.
Demonstrate mastery through a comprehensive project.
Intro
Start here
Start with Capstone and certification
Demonstrate mastery through a comprehensive project.
Demonstrate mastery through a comprehensive project.
2h
Start here
M01
Module 1
Capstone project build and evidence pack
Your capstone project is to design, build, and document a complete AI agent system that solves a real-world problem.
Core Requirements (All projects must include):
Not started
45 min
Open module
M02
Module 2
Peer review and certification readiness
Before receiving your certification, you will review another learner's project and receive feedback on yours.
Giving Feedback: Clone their repository Run their agent locally Review their documentation Test edge cases Provide constructive feedback using this template: ## Peer Review: [Project Name] ### What.
Not started
45 min
Open module
M03
Module 3
Architecture challenge simulation
Before your final assessment, test your architectural decision-making skills with this professional simulation game.
Agent Architecture Challenge.
Not started
30 min
Open module
Practice
Practice test
Capstone and certification practice test
Test recall and judgement against the governed stage question bank before you move on.
Use this after the stage modules when you want to spot weak areas without the pressure of a timed assessment. Includes 1 published questions.
Self-paced
Open practice
Test
Stage test
Capstone and certification stage test
Take the stage-end test when you want a governed timed check before the next stage.
Use this after practice when you want a stronger signal. 1 questions, 70% pass mark.
15 min
Open stage test