Ransford's Notes

Courses

Core path

Your path through this level

Progress saves in this browser and syncs after you sign in

Completed

0 of 3

You will be able to

Design a production AI system architecture with clear boundaries, failure handling, and observability.
Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.

Pick up where you left off

System shapes Scale is a trade-off Production evidence loop

Optional

Full module map

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

Show

Module 3.1System shapes

Architecture is choosing boundaries, data paths, and safe defaults, not only choosing a model.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain system shapes in your own words and apply it to a realistic scenario.
Architecture is choosing boundaries, data paths, and safe defaults, not only choosing a model.
Check the assumption "Boundaries are explicit" and explain what changes if it is false.
Check the assumption "Safety is designed in" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Boundary confusion. When people assume the model handles policy, failures become normal.
No operational plan. A system that cannot be operated safely becomes an incident generator.

Module 3.2Scale is a trade-off

Scaling increases capability and cost. Reliability comes from limits and budgets.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain scale is a trade-off in your own words and apply it to a realistic scenario.
Scaling increases capability and cost. Reliability comes from limits and budgets.
Check the assumption "Budgets are set" and explain what changes if it is false.
Check the assumption "Failure is expected" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Unbounded usage. Without budgets and limits, the system becomes expensive and unstable.
Capacity surprises. Spikes happen. If you cannot absorb spikes safely, you will fail under success.

Module 3.3Production evidence loop

In production you need evidence: monitor, respond, and improve with clear ownership.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain production evidence loop in your own words and apply it to a realistic scenario.
In production you need evidence: monitor, respond, and improve with clear ownership.
Check the assumption "Monitoring is meaningful" and explain what changes if it is false.
Check the assumption "Governance is enforced" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Metric gaming. If metrics can be gamed, quality drops while charts look good.
No incident learning. If you do not review incidents, you pay the cost repeatedly.

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 production AI system architecture with clear boundaries, failure handling, and observability.
2. Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
3. Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
4. Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

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

Modern systems

Agentic systems, safety, monitoring, and governance aligned to NIST AI RMF and ISO 23894.

Style

mixed

12 questions

Pass standard

Coming next

Not externally certified

▸Evidence you can save (CPD friendly)

A production system sketch: boundaries, permissions, fallbacks, and what is logged for audit and debugging.
A governance and risk register entry mapped to NIST AI RMF categories, with owners and evidence.
A one page incident runbook for AI failure: triage, containment, comms, and post-incident fixes.

CPD timing

Practice & Strategy time breakdown

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

Reading

34m

5,194 words × 1.3

Practice

105m

7 × 15m

Checkpoints

15m

3 × 5m

Reflection

24m

3 × 8m

Estimated total

3h 58m

Based on page content

Claimed hours

Includes reattempts + capstone

Claimed hours exceed on-page estimate by ~2h. Gap will be filled with guided practice and assessment-grade work.

CPD tracking

Fixed hours for this level are 5. 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 production AI system architecture with clear boundaries, failure handling, and observability.
2. Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
3. Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
4. Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

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

Modern systems

Agentic systems, safety, monitoring, and governance aligned to NIST AI RMF and ISO 23894.

Style

mixed

12 questions

Pass standard

Coming next

Not externally certified

▸Evidence you can save (CPD friendly)

A production system sketch: boundaries, permissions, fallbacks, and what is logged for audit and debugging.
A governance and risk register entry mapped to NIST AI RMF categories, with owners and evidence.
A one page incident runbook for AI failure: triage, containment, comms, and post-incident fixes.

Learning contract

Practice & Strategy outcomes

About 5 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 production AI system architecture with clear boundaries, failure handling, and observability.
Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

Loading content...

Next step

Practise this level, then move on

I recommend you use the practice assessment for Modern systems to test your understanding and write a short reflection. Timed assessments are being prepared for this track.

Practice

Assessment

No timer

Pace

Reflection

Evidence

Practice assessment

Start the practice assessment for Modern systems

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

Start practice assessment

The timed assessment for this level is being prepared. Use the practice assessment and labs until it is ready.

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 3

You will be able to

Design a production AI system architecture with clear boundaries, failure handling, and observability.
Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.

Pick up where you left off

System shapes Scale is a trade-off Production evidence loop

Optional

Full module map

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

Show

Module 3.1System shapes

Architecture is choosing boundaries, data paths, and safe defaults, not only choosing a model.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain system shapes in your own words and apply it to a realistic scenario.
Architecture is choosing boundaries, data paths, and safe defaults, not only choosing a model.
Check the assumption "Boundaries are explicit" and explain what changes if it is false.
Check the assumption "Safety is designed in" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Boundary confusion. When people assume the model handles policy, failures become normal.
No operational plan. A system that cannot be operated safely becomes an incident generator.

Module 3.2Scale is a trade-off

Scaling increases capability and cost. Reliability comes from limits and budgets.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain scale is a trade-off in your own words and apply it to a realistic scenario.
Scaling increases capability and cost. Reliability comes from limits and budgets.
Check the assumption "Budgets are set" and explain what changes if it is false.
Check the assumption "Failure is expected" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Unbounded usage. Without budgets and limits, the system becomes expensive and unstable.
Capacity surprises. Spikes happen. If you cannot absorb spikes safely, you will fail under success.

Module 3.3Production evidence loop

In production you need evidence: monitor, respond, and improve with clear ownership.

Open

Prerequisites

Comfort with earlier modules in this track
Ability to explain trade-offs and risks without jargon

Outcomes

Explain production evidence loop in your own words and apply it to a realistic scenario.
In production you need evidence: monitor, respond, and improve with clear ownership.
Check the assumption "Monitoring is meaningful" and explain what changes if it is false.
Check the assumption "Governance is enforced" and explain what changes if it is false.

Practice

Solve a complex scenario with explicit assumptions and constraints
Write one mitigation plan and one fallback plan

Artefact and failure modes

A concise design or governance brief that can be reviewed by a team
Metric gaming. If metrics can be gamed, quality drops while charts look good.
No incident learning. If you do not review incidents, you pay the cost repeatedly.

Optional

Planning and evidence

Objectives, timing, and CPD tracking

Show

Learning objectives

What you will be able to do

1. Design a production AI system architecture with clear boundaries, failure handling, and observability.
2. Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
3. Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
4. Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

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

Modern systems

Agentic systems, safety, monitoring, and governance aligned to NIST AI RMF and ISO 23894.

Style

mixed

12 questions

Pass standard

Coming next

Not externally certified

▸Evidence you can save (CPD friendly)

A production system sketch: boundaries, permissions, fallbacks, and what is logged for audit and debugging.
A governance and risk register entry mapped to NIST AI RMF categories, with owners and evidence.
A one page incident runbook for AI failure: triage, containment, comms, and post-incident fixes.

CPD timing

Practice & Strategy time breakdown

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

Reading

34m

5,194 words × 1.3

Practice

105m

7 × 15m

Checkpoints

15m

3 × 5m

Reflection

24m

3 × 8m

Estimated total

3h 58m

Based on page content

Claimed hours

Includes reattempts + capstone

Claimed hours exceed on-page estimate by ~2h. Gap will be filled with guided practice and assessment-grade work.

CPD tracking

Fixed hours for this level are 5. 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 production AI system architecture with clear boundaries, failure handling, and observability.
2. Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
3. Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
4. Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

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

Modern systems

Agentic systems, safety, monitoring, and governance aligned to NIST AI RMF and ISO 23894.

Style

mixed

12 questions

Pass standard

Coming next

Not externally certified

▸Evidence you can save (CPD friendly)

A production system sketch: boundaries, permissions, fallbacks, and what is logged for audit and debugging.
A governance and risk register entry mapped to NIST AI RMF categories, with owners and evidence.
A one page incident runbook for AI failure: triage, containment, comms, and post-incident fixes.

Learning contract

Practice & Strategy outcomes

About 5 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 production AI system architecture with clear boundaries, failure handling, and observability.
Evaluate cost, latency, reliability, and quality trade-offs using practical system constraints.
Define monitoring signals for drift, safety, and performance and explain how to act on them operationally.
Explain how retrieval, permissions, and data freshness change the risk profile of AI assistants.

Loading content...

Next step

Practise this level, then move on

I recommend you use the practice assessment for Modern systems to test your understanding and write a short reflection. Timed assessments are being prepared for this track.

Practice

Assessment

No timer

Pace

Reflection

Evidence

Practice assessment

Start the practice assessment for Modern systems

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

Start practice assessment

The timed assessment for this level is being prepared. Use the practice assessment and labs until it is ready.

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