Start with the person, the task, and what cannot go wrong. A useful system begins with a useful question.
Choose your pathBuild AI systems.
Explain them with confidence.
Learn the foundations, work through real designs, practise what interviewers test.
Interview this week? Go straight to the final-week review.
A little practice, right here01 / 03
- Write
- Compare
- Score
Internal knowledge assistant
Before you pick a model…
A customer wants an assistant for sensitive internal documents. What would you clarify first?
A quick preview. Your draft stays on this page.
From a Question to a System
Follow one idea from the customer’s desk to the architecture behind the answer.
Two scenes. One connected idea.
Follow the request through identity, retrieval, and an answer with evidence. Explain why each part belongs.
Explore worked designsScroll to follow the idea, or choose a scene.
Understand the problem
Start with the person, the task, and what cannot go wrong. A useful system begins with a useful question.
Choose your pathDesign the system
Follow the request through identity, retrieval, and an answer with evidence. Explain why each part belongs.
Explore worked designsNext: test the system, practise your explanation, and prepare for the interview.
What's Inside
Four areas. Learn teaches the material, the casebook and the worksheets give you real problems to work, and Interview puts it all in the order of a real loop.
Learn
547 lessons
The curriculum, from foundations to production AI, grouped by topic.
Browse the curriculumTopic groups live 6 of 9 Tracks 22 Modules 93 Notebooks 371 Casebook
33 worked designs
Complete AI system designs, each read as the spoken answer, the deep dive or the night-before review.
Open the casebookScenario packs 20 Additional system designs 9 Judgement and decomposition 4 Practice
29 worksheets
Timed worksheets. Write your answer first, then score it against a model answer.
Start practisingCustomer discovery 10 System design 12 Behavioural 7 Interview
7 rounds
The rounds of a real FDE loop, each with what it tests, what to study and how to practise.
Get interview readyMock interviews 11 Final-week reviews 18 Rounds coming soon 1
Learn by topic
- 1
Start here
2 tracks
- 2
AI Engineering
14 tracks, 371 notebooks
- 3
Production AI Engineering
1 track
- 4
Harness Engineering
Coming soon
- 5
Inference Engineering
Coming soon
- 6
AI System Design
2 tracks
- 7
Forward Deployed Engineering
1 track
- 8
Coding
Coming soon
- 9
Career
2 tracks
85 of 93 Learn modules are ready. Each module page says what is still missing. Your reading and practice progress stays in this browser.
What Makes It Different
A Judgement Layer
Every design asks why: the constraint, the trade-off, what you tell the customer.
A Casebook at Three Depths
Each case as the spoken answer, the deep dive, or the night-before review.
Rubric-Scored Practice
Write your answer first, then score it against what a strong one covers.
Built for Spoken Answers
Pages lead with the line you could say, then add depth.
Who It Is For
- Beginner
- Start from the foundations and follow one path.
- Experienced software engineer moving into AI
- Skip what you know: retrieval, agents, evaluation, production AI.
- Data engineer
- Build on the pipelines and governance you run.
- ML engineer going to production
- From a working model to a system a customer can trust.
- Architect or consultant
- Which use case to fund, what to build first, how to scope it.
- FDE candidate
- Discovery, design, behavioural stories, final-week review.
- Revision-only candidate
- Condensed reviews, worked designs, timed practice.
Know What to Study Next
Pick a path if you want a sequence. Open the curriculum if you would rather choose for yourself.