YOUR FOUNDATION-FIRST SYLLABUS
Search & grounded answers
Start with a question and a collection of documents. Learn how a system finds useful passages, builds an answer from them, and checks whether those passages actually support its claims.
0 of 87 core ideas demonstrated86 lessons1100 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 How computers represent a problem Explore everyday AI ideas; how AI got here; how computers represent a problem. 6 lessons · 0 of 6 core ideas demonstrated
08
Different ways to solve the same problem Common Ground · 11 min
To explore09 How to tell whether an AI answer is useful Common Ground · 10 min
To explore10 The questions that shaped AI Common Ground · 15 min
To explore11 How a computer stores a picture or a sentence Learning mechanisms · 16 min
To explore12 Describe a computation so someone else can follow it Learning mechanisms · 11 min
To explore13 What a representation makes easy to learn Learning mechanisms · 12 min
To exploreChapter 3 · Lessons 14–20 Turning language into model inputs Explore turning language into model inputs; finding information to support an answer; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
14
Words, structure, meaning, and context Learning mechanisms · 12 min
To explore15 Find documents through an index of their words Learning mechanisms · 14 min
To explore16 The numbers you actually need Math preparation · 10 min
To explore17 Vectors: lists that work together Math preparation · 10 min
To explore18 How text becomes tokens Learning mechanisms · 13 min
To explore19 From token IDs to learned vectors Learning mechanisms · 14 min
To explore20 Search learned representations with approximate neighbors Learning mechanisms · 14 min
To exploreChapter 4 · Lessons 21–27 Learning from useful data: From the world to a dataset Explore learning from useful data; finding information to support an answer; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
21
From the world to a dataset Learning mechanisms · 11 min
To explore22 Where did this dataset come from? Learning mechanisms · 12 min
To explore23 Prepare retrievable evidence without losing its context Learning mechanisms · 10 min
To explore24 Improve candidate retrieval and rank the useful evidence Learning mechanisms · 13 min
To explore25 Probability without the mystery Math preparation · 10 min
To explore26 A function is a rule Math preparation · 9 min
To explore27 Powers and logarithms, one step at a time Math preparation · 11 min
To exploreChapter 5 · Lessons 28–34 Following attention through a transformer Explore turning language into model inputs; finding information to support an answer; following attention through a transformer; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
28
How a language model takes its next step Your system, connected · 15 min
To explore29 Retrieve evidence and condition an answer on it Learning mechanisms · 11 min
To explore30 Attention: queries, keys, and values Learning mechanisms · 13 min
To explore31 From attention scores to a causal mask Learning mechanisms · 17 min
To explore32 Build a tiny prediction model Learning mechanisms · 11 min
To explore33 Inside an artificial neuron Learning mechanisms · 14 min
To explore34 Why layers need more than multiplication Learning mechanisms · 12 min
To exploreChapter 6 · Lessons 35–41 Learning from useful data: Clean data without erasing the problem Explore following attention through a transformer; helping a model improve; preparing and training a language model; and supporting ideas. 7 lessons · 0 of 8 core ideas demonstrated
35
Follow one token through a transformer Your system, connected · 13 min
To explore36 How does a model improve a prediction? Learning mechanisms · 32 min
To explore37 Inside a language model training step Learning mechanisms · 14 min
To explore38 Averages over uncertain outcomes Math preparation · 9 min
To explore39 What can a small experiment tell us? Math preparation · 10 min
To explore40 Clean data without erasing the problem Learning mechanisms · 12 min
To explore41 Protect the examples used to judge a model Learning mechanisms · 15 min
To exploreChapter 7 · Lessons 42–48 Preparing and training a language model: Assemble token batches without leaking targets Explore preparing and training a language model; following attention through a transformer; inside a neural network; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
42
Assemble token batches without leaking targets Learning mechanisms · 14 min
To explore43 Choose what a pretraining prediction means Learning mechanisms · 13 min
To explore44 Read an equation one symbol at a time Math preparation · 10 min
To explore45 Follow shapes through a numerical layer Math preparation · 10 min
To explore46 Run several learned comparisons in parallel Learning mechanisms · 10 min
To explore47 Trace inputs through layers to a loss Learning mechanisms · 17 min
To explore48 A derivative is a local change Math preparation · 13 min
To exploreChapter 8 · Lessons 49–56 Inside a neural network Explore inside a neural network; learning from sequences and sound; following attention through a transformer; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
49
The chain rule, one step at a time Math preparation · 13 min
To explore50 How an error reaches earlier weights Learning mechanisms · 11 min
To explore51 Let the graph carry derivatives Learning mechanisms · 12 min
To explore52 Carry a state from one step to the next Learning mechanisms · 14 min
To explore53 Map one sequence into another Learning mechanisms · 17 min
To explore54 Match information flow to the learning objective Learning mechanisms · 13 min
To explore55 Represent text with counts and short contexts Learning mechanisms · 14 min
To explore56 Learn the units used by a language model Learning mechanisms · 15 min
To exploreChapter 9 · Lessons 57–63 Helping a model improve Explore helping a model improve; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
57
Learn from a sample of examples at each step Learning mechanisms · 11 min
To explore58 Several inputs, several rates of change Math preparation · 9 min
To explore59 Choose a direction and a step size Math preparation · 9 min
To explore60 How momentum and Adam use earlier gradients Learning mechanisms · 15 min
To explore61 Constrain a solution or change the update Learning mechanisms · 12 min
To explore62 When the computer cannot store the exact number Math preparation · 12 min
To explore63 Keep signals and gradients in a usable range Learning mechanisms · 12 min
To exploreChapter 10 · Lessons 64–70 Preparing and training a language model: Choose the model that pretraining will fit Explore inside a neural network; preparing and training a language model; learning to predict. 7 lessons · 0 of 7 core ideas demonstrated
64
Help information and learning signals travel Learning mechanisms · 12 min
To explore65 Connect data, gradients, and saved model state Learning mechanisms · 15 min
To explore66 Choose the model that pretraining will fit Learning mechanisms · 15 min
To explore67 Build a traceable corpus before spending training compute Learning mechanisms · 19 min
To explore68 Choose how much the model sees of each source Learning mechanisms · 13 min
To explore69 Turn a linear score into a class probability Learning mechanisms · 11 min
To explore70 Control complexity without peeking at the answer Learning mechanisms · 12 min
To exploreChapter 11 · Lessons 71–78 Testing what a model has learned Explore testing what a model has learned; preparing and training a language model; following attention through a transformer; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
71
Will the model work on new examples? Learning mechanisms · 14 min
To explore72 Why a simpler model can predict better Learning mechanisms · 14 min
To explore73 Evaluate the procedure that chose the model Learning mechanisms · 14 min
To explore74 More capacity changes more than one thing Learning mechanisms · 14 min
To explore75 Allocate compute and preserve useful checkpoints Learning mechanisms · 15 min
To explore76 Distances, neighborhoods, and transformations Math preparation · 12 min
To explore77 Give a transformer information about order Learning mechanisms · 12 min
To explore78 Continue pretraining without losing sight of the starting model Learning mechanisms · 12 min
To exploreChapter 12 · Lessons 79–86 Building an agent that uses tools Explore adapting a model after pretraining; giving a model time to reason; finding information to support an answer; and supporting ideas. 8 lessons · 0 of 8 core ideas demonstrated
79
Track what each adaptation stage changes Learning mechanisms · 15 min
To explore80 Separate a correct solution from a convincing explanation Learning mechanisms · 12 min
To explore81 Check whether a source supports the claim beside it Learning mechanisms · 14 min
To explore82 Decide where a system follows a workflow and where it chooses actions Learning mechanisms · 12 min
To explore83 Give tools clear inputs, results, and state Learning mechanisms · 14 min
To explore84 Decide what to retain and what to show the model now Learning mechanisms · 12 min
To explore85 Keep the authority to act outside retrieved content Learning mechanisms · 14 min
To explore86 Keep retrieved evidence current, permitted, and resistant to manipulation Learning mechanisms · 11 min
To exploreOptional extensions and comparisons (7)
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.Choose an answer from a listFast typed decisions for routing and triage: when a small decision model beats a chat model.Prompting in practice: instructions, examples, and step-by-step requestsGet better answers from any chat assistant today: say what you want, show an example, give it the facts, and check what comes back.Choose how information should reach the modelDecide when to retrieve, paste the whole source into the prompt, or fine-tune, using a needs table and token-cost arithmetic.Store relationships so they can be queriedStore facts as linked entities that retrieval can follow, the structured cousin of a search index.Project: trace a grounded answer and a controlled tool actionBuild a small grounded answerer with a guarded tool action, on paper or in code.