YOUR FOUNDATION-FIRST SYLLABUS
Fast decision models
Start with a support desk that needs thousands of quick routing and triage calls a day. Learn how System One decision models return typed answers with probabilities instead of text, and how to build and judge systems around them.
0 of 48 core ideas demonstrated48 lessons710 estimated minutes remaining
Already know some of this?
Go straight to an idea’s knowledge check. Passing its different checks without hints carries that evidence into this path. Checking an advanced idea does not award its prerequisites; you can still explore them.
Check what I already knowTHE IDEAS, IN ORDER
Shared credit is automaticBuild your understanding.
Chapter counts use compatible knowledge-check evidence. Reading a lesson does not mark its ideas as demonstrated.
Chapter 1 · Lessons 1–7 Meet an AI system Start with an everyday task, then follow its inputs, model, and output. 7 lessons · 0 of 7 core ideas demonstrated Up next
01
What is AI? Start with an everyday task Common Ground · 11 min
To explore02 Inputs and outputs: what goes in and what comes out Common Ground · 13 min
To explore03 Data and examples: what a computer can learn from Common Ground · 10 min
To explore04 What is a model? A small rule inside a bigger app Common Ground · 10 min
To explore05 Weights: the adjustable numbers in a model Common Ground · 12 min
To explore06 Training and inference: changing a rule or using it Common Ground · 13 min
To explore07 Follow one small AI system from start to finish Common Ground · 9 min
To exploreChapter 2 · Lessons 8–13 Build your AI compass Explore everyday AI ideas; how computers represent a problem; learning from useful data; and supporting ideas. 6 lessons · 0 of 6 core ideas demonstrated
08
How to tell whether an AI answer is useful Common Ground · 10 min
To explore09 How a computer stores a picture or a sentence Learning mechanisms · 16 min
To explore10 Different ways to solve the same problem Common Ground · 11 min
To explore11 What a representation makes easy to learn Learning mechanisms · 12 min
To explore12 From the world to a dataset Learning mechanisms · 11 min
To explore13 The numbers you actually need Math preparation · 10 min
To exploreChapter 3 · Lessons 14–19 Learning to predict Explore learning to predict; math preparation when it is needed. 6 lessons · 0 of 6 core ideas demonstrated
14
A function is a rule Math preparation · 9 min
To explore15 Build a tiny prediction model Learning mechanisms · 11 min
To explore16 Probability without the mystery Math preparation · 10 min
To explore17 Powers and logarithms, one step at a time Math preparation · 11 min
To explore18 Turn a linear score into a class probability Learning mechanisms · 11 min
To explore19 Averages over uncertain outcomes Math preparation · 9 min
To exploreChapter 4 · Lessons 20–26 Turning language into model inputs Explore learning from useful data; learning to predict; turning language into model inputs; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
20
Who is represented by the data? Learning mechanisms · 14 min
To explore21 Decide what success means before training Learning mechanisms · 12 min
To explore22 Look inside the average score Learning mechanisms · 14 min
To explore23 How text becomes tokens Learning mechanisms · 13 min
To explore24 Vectors: lists that work together Math preparation · 10 min
To explore25 From token IDs to learned vectors Learning mechanisms · 14 min
To explore26 How a language model takes its next step Your system, connected · 15 min
To exploreChapter 5 · Lessons 27–33 Tools for thinking about models: Choose an answer from a list Explore connected AI ideas; following attention through a transformer; working with uncertainty; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
27
Choose an answer from a list Learning mechanisms · 20 min
To explore28 Write questions the model can answer Learning mechanisms · 23 min
To explore29 Attention: queries, keys, and values Learning mechanisms · 13 min
To explore30 How the model scores your choices Learning mechanisms · 20 min
To explore31 Probability, likelihood, and what is unknown Learning mechanisms · 11 min
To explore32 Update a belief using new evidence Learning mechanisms · 13 min
To explore33 Value a choice and its later consequences Math preparation · 12 min
To exploreChapter 6 · Lessons 34–40 Tools for thinking about models: Train and check probabilities Explore working with uncertainty; connected AI ideas; learning from useful data; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
34
Turn a probability into a justified action Learning mechanisms · 11 min
To explore35 Train and check probabilities Learning mechanisms · 24 min
To explore36 Build a router that knows when to ask Learning mechanisms · 29 min
To explore37 What can a small experiment tell us? Math preparation · 10 min
To explore38 Clean data without erasing the problem Learning mechanisms · 12 min
To explore39 Protect the examples used to judge a model Learning mechanisms · 15 min
To explore40 Control complexity without peeking at the answer Learning mechanisms · 12 min
To exploreChapter 7 · Lessons 41–48 Testing what a model has learned Explore testing what a model has learned; how computers represent a problem; checking reliability and behavior; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
41
Evaluate the procedure that chose the model Learning mechanisms · 14 min
To explore42 Change one thing and measure what follows Learning mechanisms · 13 min
To explore43 Describe a computation so someone else can follow it Learning mechanisms · 11 min
To explore44 Repeat an experiment without confusing luck with truth Learning mechanisms · 11 min
To explore45 Make the result possible to inspect Learning mechanisms · 12 min
To explore46 Measure the behavior that the task actually needs Learning mechanisms · 14 min
To explore47 Compare decision models fairly Learning mechanisms · 21 min
To explore48 Project: build and gate a tiny router Learning mechanisms · 90 min
To exploreOptional extensions and comparisons (5)
These lessons deepen or compare the reference design. They do not add requirements to this path’s completion.
How to use this school without getting lostOptional orientation: how paths, side lessons, and practice fit together, plus study habits that make learning stick.Practice, progress, and knowing what you understandOptional orientation: use practice, mistakes, and spaced review to find out what you really understand.Prompting in practice: instructions, examples, and step-by-step requestsDecision models answer typed questions; chat models answer prompts. See how the two styles of instruction differ.Give people useful control over model-assisted workDesign the human side of confidence routing: review queues, thresholds, and automation bias.Decide where a system follows a workflow and where it chooses actionsSee where a fast decision step fits inside a larger agent or workflow.