AI Agents course

You are inworkspace

Core path

Your path through this level

Progress saves in this browser and syncs after you sign in

Completed

0 of 5

Pick up where you left off

Learning from patterns From chat to action Talking to the computer directly Reproducible environments Prompt, response, verification

Optional

Full module map

Use this if you want the shape of the level before you start

Show

Module 1.1Learning from patterns

Modern AI mostly learns patterns from data, then uses them to predict what comes next.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain learning from patterns in your own words and apply it to a realistic scenario.
Modern AI mostly learns patterns from data, then uses them to predict what comes next.
Check the assumption "Data reflects reality" and explain what changes if it is false.
Check the assumption "The metric matches the goal" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Spurious patterns. A model can learn shortcuts that look correct in training data, then fail badly in the real world.
Distribution shift. When the world changes, yesterday's patterns stop being reliable.

Module 1.2From chat to action

An agent is a loop that can plan, act with tools, observe results, then decide what to do next.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain from chat to action in your own words and apply it to a realistic scenario.
An agent is a loop that can plan, act with tools, observe results, then decide what to do next.
Check the assumption "Tools have clear contracts" and explain what changes if it is false.
Check the assumption "The loop is bounded" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Tool misuse. If a tool can do too much, a small mistake becomes a big incident.
Runaway loops. Without stop conditions, an agent can keep calling tools and never deliver a result.

Module 1.3Talking to the computer directly

The command line is a precise way to tell your computer what to do, and to see what it actually did.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain talking to the computer directly in your own words and apply it to a realistic scenario.
The command line is a precise way to tell your computer what to do, and to see what it actually did.
Check the assumption "Commands are intentional" and explain what changes if it is false.
Check the assumption "You know where you are" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Destructive defaults. Some commands do not ask twice. Use dry runs and explicit flags when you can.
Hidden environment changes. A command can update your environment and later steps fail in surprising ways.

Module 1.4Reproducible environments

A good environment setup makes builds repeatable and keeps secrets out of the codebase.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain reproducible environments in your own words and apply it to a realistic scenario.
A good environment setup makes builds repeatable and keeps secrets out of the codebase.
Check the assumption "Versions are pinned" and explain what changes if it is false.
Check the assumption "Secrets are separated" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Works on my machine. Unpinned dependencies make local success meaningless.
Secret leakage. If a key reaches a repo or client logs, treat it as compromised and rotate it.

Module 1.5Prompt, response, verification

A useful first habit is to treat model output as a draft that you verify, not a fact you obey.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain prompt, response, verification in your own words and apply it to a realistic scenario.
A useful first habit is to treat model output as a draft that you verify, not a fact you obey.
Check the assumption "You validate claims" and explain what changes if it is false.
Check the assumption "You state constraints" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Confident mistakes. Models can sound certain while being wrong. Confidence is not a guarantee.
Over trust. If you treat output as authority, you outsource judgement and take on hidden risk.

What changes at this level

Level expectations

Each level is independent but clearly deeper than the last. This panel makes the jump explicit.

Learning contract

Practice assessment outcomes

Read the explanation first, then use the tools to test the idea. Skip any tool that is not useful for your goal.

This is a scored practice assessment. It is free and not timed. Use it to sharpen judgement before the timed stage assessment.

Practice assessment bank not found for this level yet.

What to do next

Write a short review note on one miss and the assumption behind it.
Add one concrete guardrail that would have prevented that miss.
Retake the practice set, then move to the timed stage assessment.

Start timed assessment CPD prep pack Back to stage

Course materials are protected by intellectual property rights.View terms

Loading lesson...

Core path

Your path through this level

Progress saves in this browser and syncs after you sign in

Completed

0 of 5

Pick up where you left off

Learning from patterns From chat to action Talking to the computer directly Reproducible environments Prompt, response, verification

Optional

Full module map

Use this if you want the shape of the level before you start

Show

Module 1.1Learning from patterns

Modern AI mostly learns patterns from data, then uses them to predict what comes next.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain learning from patterns in your own words and apply it to a realistic scenario.
Modern AI mostly learns patterns from data, then uses them to predict what comes next.
Check the assumption "Data reflects reality" and explain what changes if it is false.
Check the assumption "The metric matches the goal" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Spurious patterns. A model can learn shortcuts that look correct in training data, then fail badly in the real world.
Distribution shift. When the world changes, yesterday's patterns stop being reliable.

Module 1.2From chat to action

An agent is a loop that can plan, act with tools, observe results, then decide what to do next.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain from chat to action in your own words and apply it to a realistic scenario.
An agent is a loop that can plan, act with tools, observe results, then decide what to do next.
Check the assumption "Tools have clear contracts" and explain what changes if it is false.
Check the assumption "The loop is bounded" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Tool misuse. If a tool can do too much, a small mistake becomes a big incident.
Runaway loops. Without stop conditions, an agent can keep calling tools and never deliver a result.

Module 1.3Talking to the computer directly

The command line is a precise way to tell your computer what to do, and to see what it actually did.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain talking to the computer directly in your own words and apply it to a realistic scenario.
The command line is a precise way to tell your computer what to do, and to see what it actually did.
Check the assumption "Commands are intentional" and explain what changes if it is false.
Check the assumption "You know where you are" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Destructive defaults. Some commands do not ask twice. Use dry runs and explicit flags when you can.
Hidden environment changes. A command can update your environment and later steps fail in surprising ways.

Module 1.4Reproducible environments

A good environment setup makes builds repeatable and keeps secrets out of the codebase.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain reproducible environments in your own words and apply it to a realistic scenario.
A good environment setup makes builds repeatable and keeps secrets out of the codebase.
Check the assumption "Versions are pinned" and explain what changes if it is false.
Check the assumption "Secrets are separated" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Works on my machine. Unpinned dependencies make local success meaningless.
Secret leakage. If a key reaches a repo or client logs, treat it as compromised and rotate it.

Module 1.5Prompt, response, verification

A useful first habit is to treat model output as a draft that you verify, not a fact you obey.

Open

Prerequisites

No previous technical background required
Read the section explanation before using tools

Outcomes

Explain prompt, response, verification in your own words and apply it to a realistic scenario.
A useful first habit is to treat model output as a draft that you verify, not a fact you obey.
Check the assumption "You validate claims" and explain what changes if it is false.
Check the assumption "You state constraints" and explain what changes if it is false.

Practice

Complete one guided exercise and explain your decision in plain language
Use the recap only after reading the main section

Artefact and failure modes

A short module note with one key definition and one practical example
Confident mistakes. Models can sound certain while being wrong. Confidence is not a guarantee.
Over trust. If you treat output as authority, you outsource judgement and take on hidden risk.

What changes at this level

Level expectations

Each level is independent but clearly deeper than the last. This panel makes the jump explicit.

Learning contract

Practice assessment outcomes

Read the explanation first, then use the tools to test the idea. Skip any tool that is not useful for your goal.

This is a scored practice assessment. It is free and not timed. Use it to sharpen judgement before the timed stage assessment.

Practice assessment bank not found for this level yet.

What to do next

Write a short review note on one miss and the assumption behind it.
Add one concrete guardrail that would have prevented that miss.
Retake the practice set, then move to the timed stage assessment.

Start timed assessment CPD prep pack Back to stage

Course materials are protected by intellectual property rights.View terms

AI agents practice assessment. Foundations

Level expectations

Practice assessment outcomes

AI agents practice assessment. Foundations

Level expectations

Practice assessment outcomes