AI Agents course

Core path

Your path through this level

Progress saves in this browser and syncs after you sign in

Completed

0 of 5

You will be able to

Design a tool schema that an agent can use safely
Choose between short term and long term memory and explain why
Map a reasoning loop that includes planning, acting, and checking

Pick up where you left off

Reasoning as a loop Tools as controlled capability Context is a budget Patterns reduce surprises Boundaries make systems safe

Optional

Full module map

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

Show

Module 2.1Reasoning as a loop

Agent behaviour is usually a loop that updates its plan based on observations.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain reasoning as a loop in your own words and apply it to a realistic scenario.
Agent behaviour is usually a loop that updates its plan based on observations.
Check the assumption "State is tracked" and explain what changes if it is false.
Check the assumption "Stop rules exist" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Overthinking. Too much reasoning can increase latency and cost without improving outcomes.
Looping on ambiguity. If the agent cannot resolve missing information, it can cycle between tool calls and guesses.

Module 2.2Tools as controlled capability

Tools turn text into real actions. That is powerful, and it is where most safety work lives.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain tools as controlled capability in your own words and apply it to a realistic scenario.
Tools turn text into real actions. That is powerful, and it is where most safety work lives.
Check the assumption "Tool schemas are accurate" and explain what changes if it is false.
Check the assumption "Outputs are validated" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Wrong tool selection. If the agent calls the wrong tool, it can create bad side effects or leak data.
Unbounded capability. A tool that can do anything becomes a security incident waiting for a prompt.

Module 2.3Context is a budget

Context windows are limited. Memory systems extend context, but they also introduce new risks.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain context is a budget in your own words and apply it to a realistic scenario.
Context windows are limited. Memory systems extend context, but they also introduce new risks.
Check the assumption "Memory is relevant" and explain what changes if it is false.
Check the assumption "Sensitive data is protected" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Leaky recall. If retrieval is not filtered, the model can pull in private or unrelated information.
Stale assumptions. Old memory can override new instructions and create confusing behaviour.

Module 2.4Patterns reduce surprises

Design patterns give you a known shape so you can test, monitor, and debug agent behaviour.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain patterns reduce surprises in your own words and apply it to a realistic scenario.
Design patterns give you a known shape so you can test, monitor, and debug agent behaviour.
Check the assumption "Roles are clear" and explain what changes if it is false.
Check the assumption "Checks run by default" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Pattern mismatch. A complex pattern for a simple task adds cost and new ways to fail.
Hidden coupling. If multiple roles share hidden state, debugging becomes story telling.

Module 2.5Boundaries make systems safe

A good architecture makes boundaries explicit so tools and data do not leak across them.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain boundaries make systems safe in your own words and apply it to a realistic scenario.
A good architecture makes boundaries explicit so tools and data do not leak across them.
Check the assumption "Trust boundaries are enforced" and explain what changes if it is false.
Check the assumption "Least privilege is real" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Accidental data exposure. If the agent can reach sensitive data by default, it will leak it eventually.
No safe failure. If everything depends on the agent being perfect, the system is not production ready.

Optional

Planning and evidence

Objectives, timing, and CPD tracking

Show

If you want to start learning now, leave this closed. Come back when you want to plan your practice or keep evidence for CPD. This is guidance and it is not endorsed by awarding bodies. Standards mapping lives on the course overview page.

Learning objectives

What you will be able to do

1. Design a tool schema that an agent can use safely
Reasoning loops are the heartbeat of an agent, so we make them explicit.
2. Choose between short term and long term memory and explain why
Tool schemas stop agents from guessing and help them act safely.
3. Map a reasoning loop that includes planning, acting, and checking
Memory choices decide what the agent can remember and what it should forget.
4. Spot common failure modes in a simple workflow
Designing for failure is what keeps agents reliable in the real world.

What comes next

Next we build full workflows because that is where theory becomes skill.

Continue to Practical building

What changes at this level

Level expectations

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

Assessment intent

Core concepts

Reasoning loops, tool contracts, and memory design that stand up under pressure.

Style

mixed

50 questions

75 min timed

Pass standard

70%

Not externally certified

CPD timing

Core Concepts time breakdown

Defensible timing based on page content: reading, labs, checkpoints, and reflection.

Reading

42m

6,329 words × 1.3

Practice

15m

1 × 15m

Checkpoints

40m

8 × 5m

Reflection

40m

5 × 8m

Estimated total

2h 17m

Based on page content

Claimed hours

25h

Includes reattempts + capstone

Claimed hours exceed on-page estimate by ~23h. Gap will be filled with guided practice and assessment-grade work.

CPD tracking

Fixed hours for this level are 25. Timed assessment time is included once on pass.

View in My CPD

Pricing and CPD Sign in to sync progress and unlock assessments

Progress minutes

0.0 hours

Learning objectives

What you will be able to do

1. Design a tool schema that an agent can use safely
Reasoning loops are the heartbeat of an agent, so we make them explicit.
2. Choose between short term and long term memory and explain why
Tool schemas stop agents from guessing and help them act safely.
3. Map a reasoning loop that includes planning, acting, and checking
Memory choices decide what the agent can remember and what it should forget.
4. Spot common failure modes in a simple workflow
Designing for failure is what keeps agents reliable in the real world.

What comes next

Next we build full workflows because that is where theory becomes skill.

Continue to Practical building

What changes at this level

Level expectations

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

Assessment intent

Core concepts

Reasoning loops, tool contracts, and memory design that stand up under pressure.

Style

mixed

50 questions

75 min timed

Pass standard

70%

Not externally certified

Learning contract

Core Concepts outcomes

About 25 hours

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

Design a tool schema that an agent can use safely
Choose between short term and long term memory and explain why
Map a reasoning loop that includes planning, acting, and checking
Spot common failure modes in a simple workflow

Loading content...

Next step

Practise this level, then take the timed assessment

I recommend you start with the practice assessment for Core concepts. It is not timed and it helps you write a clear CPD reflection before the full assessment.

Questions

Minutes

70%

Pass mark

Practice assessment

Start the practice assessment for Core concepts

It is designed for confidence and evidence, and you can retry as often as you need.

Start practice assessment

Full assessment

AI Agents Core concepts assessment

This assessment is timed. It is free to take and you can retry as often as you need.

Detailed feedback on every question
Pass evidence recorded in your account on pass
Personalised recommendations on weak areas

You can complete the course while signed out, and your progress saves in this browser. Sign in before assessments so your pass record is attached to your account.

Courses and assessments are free. There is no paywall for the learning path, practice questions, or formal assessments. Optional donations support hosting, maintenance, and ongoing updates.

During timed assessments, copy and the context menu are restricted to reduce casual cheating. Passed assessments are recorded in your account as evidence.

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

You will be able to

Design a tool schema that an agent can use safely
Choose between short term and long term memory and explain why
Map a reasoning loop that includes planning, acting, and checking

Pick up where you left off

Reasoning as a loop Tools as controlled capability Context is a budget Patterns reduce surprises Boundaries make systems safe

Optional

Full module map

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

Show

Module 2.1Reasoning as a loop

Agent behaviour is usually a loop that updates its plan based on observations.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain reasoning as a loop in your own words and apply it to a realistic scenario.
Agent behaviour is usually a loop that updates its plan based on observations.
Check the assumption "State is tracked" and explain what changes if it is false.
Check the assumption "Stop rules exist" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Overthinking. Too much reasoning can increase latency and cost without improving outcomes.
Looping on ambiguity. If the agent cannot resolve missing information, it can cycle between tool calls and guesses.

Module 2.2Tools as controlled capability

Tools turn text into real actions. That is powerful, and it is where most safety work lives.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain tools as controlled capability in your own words and apply it to a realistic scenario.
Tools turn text into real actions. That is powerful, and it is where most safety work lives.
Check the assumption "Tool schemas are accurate" and explain what changes if it is false.
Check the assumption "Outputs are validated" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Wrong tool selection. If the agent calls the wrong tool, it can create bad side effects or leak data.
Unbounded capability. A tool that can do anything becomes a security incident waiting for a prompt.

Module 2.3Context is a budget

Context windows are limited. Memory systems extend context, but they also introduce new risks.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain context is a budget in your own words and apply it to a realistic scenario.
Context windows are limited. Memory systems extend context, but they also introduce new risks.
Check the assumption "Memory is relevant" and explain what changes if it is false.
Check the assumption "Sensitive data is protected" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Leaky recall. If retrieval is not filtered, the model can pull in private or unrelated information.
Stale assumptions. Old memory can override new instructions and create confusing behaviour.

Module 2.4Patterns reduce surprises

Design patterns give you a known shape so you can test, monitor, and debug agent behaviour.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain patterns reduce surprises in your own words and apply it to a realistic scenario.
Design patterns give you a known shape so you can test, monitor, and debug agent behaviour.
Check the assumption "Roles are clear" and explain what changes if it is false.
Check the assumption "Checks run by default" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Pattern mismatch. A complex pattern for a simple task adds cost and new ways to fail.
Hidden coupling. If multiple roles share hidden state, debugging becomes story telling.

Module 2.5Boundaries make systems safe

A good architecture makes boundaries explicit so tools and data do not leak across them.

Open

Prerequisites

Foundations-level understanding of this course
Confidence with key terms introduced in Stage 1

Outcomes

Explain boundaries make systems safe in your own words and apply it to a realistic scenario.
A good architecture makes boundaries explicit so tools and data do not leak across them.
Check the assumption "Trust boundaries are enforced" and explain what changes if it is false.
Check the assumption "Least privilege is real" and explain what changes if it is false.

Practice

Run the section simulator and map each step to an explicit decision
Explain one assumption and how you would test it

Artefact and failure modes

A short architecture note that names tool choice, memory choice, and risk
Accidental data exposure. If the agent can reach sensitive data by default, it will leak it eventually.
No safe failure. If everything depends on the agent being perfect, the system is not production ready.

Optional

Planning and evidence

Objectives, timing, and CPD tracking

Show

Learning objectives

What you will be able to do

1. Design a tool schema that an agent can use safely
Reasoning loops are the heartbeat of an agent, so we make them explicit.
2. Choose between short term and long term memory and explain why
Tool schemas stop agents from guessing and help them act safely.
3. Map a reasoning loop that includes planning, acting, and checking
Memory choices decide what the agent can remember and what it should forget.
4. Spot common failure modes in a simple workflow
Designing for failure is what keeps agents reliable in the real world.

What comes next

Next we build full workflows because that is where theory becomes skill.

Continue to Practical building

What changes at this level

Level expectations

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

Assessment intent

Core concepts

Reasoning loops, tool contracts, and memory design that stand up under pressure.

Style

mixed

50 questions

75 min timed

Pass standard

70%

Not externally certified

CPD timing

Core Concepts time breakdown

Defensible timing based on page content: reading, labs, checkpoints, and reflection.

Reading

42m

6,329 words × 1.3

Practice

15m

1 × 15m

Checkpoints

40m

8 × 5m

Reflection

40m

5 × 8m

Estimated total

2h 17m

Based on page content

Claimed hours

25h

Includes reattempts + capstone

Claimed hours exceed on-page estimate by ~23h. Gap will be filled with guided practice and assessment-grade work.

CPD tracking

Fixed hours for this level are 25. Timed assessment time is included once on pass.

View in My CPD

Pricing and CPD Sign in to sync progress and unlock assessments

Progress minutes

0.0 hours

Learning objectives

What you will be able to do

1. Design a tool schema that an agent can use safely
Reasoning loops are the heartbeat of an agent, so we make them explicit.
2. Choose between short term and long term memory and explain why
Tool schemas stop agents from guessing and help them act safely.
3. Map a reasoning loop that includes planning, acting, and checking
Memory choices decide what the agent can remember and what it should forget.
4. Spot common failure modes in a simple workflow
Designing for failure is what keeps agents reliable in the real world.

What comes next

Next we build full workflows because that is where theory becomes skill.

Continue to Practical building

What changes at this level

Level expectations

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

Assessment intent

Core concepts

Reasoning loops, tool contracts, and memory design that stand up under pressure.

Style

mixed

50 questions

75 min timed

Pass standard

70%

Not externally certified

Learning contract

Core Concepts outcomes

About 25 hours

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

Design a tool schema that an agent can use safely
Choose between short term and long term memory and explain why
Map a reasoning loop that includes planning, acting, and checking
Spot common failure modes in a simple workflow

Loading content...

Next step

Practise this level, then take the timed assessment

I recommend you start with the practice assessment for Core concepts. It is not timed and it helps you write a clear CPD reflection before the full assessment.

Questions

Minutes

70%

Pass mark

Practice assessment

Start the practice assessment for Core concepts

It is designed for confidence and evidence, and you can retry as often as you need.

Start practice assessment

Full assessment

AI Agents Core concepts assessment

This assessment is timed. It is free to take and you can retry as often as you need.

Detailed feedback on every question
Pass evidence recorded in your account on pass
Personalised recommendations on weak areas

You can complete the course while signed out, and your progress saves in this browser. Sign in before assessments so your pass record is attached to your account.

Courses and assessments are free. There is no paywall for the learning path, practice questions, or formal assessments. Optional donations support hosting, maintenance, and ongoing updates.

During timed assessments, copy and the context menu are restricted to reduce casual cheating. Passed assessments are recorded in your account as evidence.

Course materials are protected by intellectual property rights.View terms

Stage 2. Core concepts

What you will be able to do

Level expectations

Core Concepts time breakdown

What you will be able to do

Level expectations

Core Concepts outcomes

Practise this level, then take the timed assessment

Start the practice assessment for Core concepts

AI Agents Core concepts assessment

Stage 2. Core concepts

What you will be able to do

Level expectations

Core Concepts time breakdown

What you will be able to do

Level expectations

Core Concepts outcomes

Practise this level, then take the timed assessment

Start the practice assessment for Core concepts

AI Agents Core concepts assessment