YOUR FOUNDATION-FIRST SYLLABUS
Agents & tool workflows
Follow an AI system as it chooses a tool, gives it instructions, checks what happened, and recovers from a mistake. Build from ordinary programs to a small workflow with clear limits.
0 of 71 core ideas demonstrated71 lessons950 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 8–14 How computers represent a problem Explore everyday AI ideas; how AI got here; how computers represent a problem; and supporting ideas. 7 lessons · 0 of 7 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 explore14 How text becomes tokens Learning mechanisms · 13 min
To exploreChapter 3 · Lessons 15–21 Turning language into model inputs Explore turning language into model inputs; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
15
The numbers you actually need Math preparation · 10 min
To explore16 Vectors: lists that work together Math preparation · 10 min
To explore17 From token IDs to learned vectors Learning mechanisms · 14 min
To explore18 Probability without the mystery Math preparation · 10 min
To explore19 A function is a rule Math preparation · 9 min
To explore20 Powers and logarithms, one step at a time Math preparation · 11 min
To explore21 How a language model takes its next step Your system, connected · 15 min
To exploreChapter 4 · Lessons 22–28 Reasoning with facts and rules Explore building an agent that uses tools; searching and planning; reasoning with facts and rules; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
22
Decide where a system follows a workflow and where it chooses actions Learning mechanisms · 12 min
To explore23 Give tools clear inputs, results, and state Learning mechanisms · 14 min
To explore24 Sets, graphs, and counting possibilities Math preparation · 10 min
To explore25 Turn a goal into states and actions Learning mechanisms · 13 min
To explore26 Reason with statements that are true or false Learning mechanisms · 13 min
To explore27 Talk about objects and relationships Learning mechanisms · 12 min
To explore28 From facts to conclusions—and backward from a goal Learning mechanisms · 12 min
To exploreChapter 5 · Lessons 29–35 Building an agent that uses tools Explore searching and planning; building an agent that uses tools; turning language into model inputs; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
29
Represent what an action requires and changes Learning mechanisms · 14 min
To explore30 Turn a plan into checked execution with recovery paths Learning mechanisms · 14 min
To explore31 Words, structure, meaning, and context Learning mechanisms · 12 min
To explore32 Find documents through an index of their words Learning mechanisms · 14 min
To explore33 Decide what to retain and what to show the model now Learning mechanisms · 12 min
To explore34 Keep the authority to act outside retrieved content Learning mechanisms · 14 min
To explore35 Averages over uncertain outcomes Math preparation · 9 min
To exploreChapter 6 · Lessons 36–42 Learning from useful data Explore learning from useful data; learning to predict; math preparation when it is needed. 7 lessons · 0 of 7 core ideas demonstrated
36
What can a small experiment tell us? Math preparation · 10 min
To explore37 From the world to a dataset Learning mechanisms · 11 min
To explore38 Build a tiny prediction model Learning mechanisms · 11 min
To explore39 Turn a linear score into a class probability Learning mechanisms · 11 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 explore42 Control complexity without peeking at the answer Learning mechanisms · 12 min
To exploreChapter 7 · Lessons 43–49 Testing what a model has learned Explore testing what a model has learned; how computers represent a problem; building an agent that uses tools; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
43
Evaluate the procedure that chose the model Learning mechanisms · 14 min
To explore44 Change one thing and measure what follows Learning mechanisms · 13 min
To explore45 Repeat an experiment without confusing luck with truth Learning mechanisms · 11 min
To explore46 Make the result possible to inspect Learning mechanisms · 12 min
To explore47 Evaluate the completed task and the trajectory that produced it Learning mechanisms · 14 min
To explore48 Search learned representations with approximate neighbors Learning mechanisms · 14 min
To explore49 Where did this dataset come from? Learning mechanisms · 12 min
To exploreChapter 8 · Lessons 50–56 Finding information to support an answer Explore finding information to support an answer; making responsible system decisions; learning from useful data. 7 lessons · 0 of 7 core ideas demonstrated
50
Prepare retrievable evidence without losing its context Learning mechanisms · 10 min
To explore51 Improve candidate retrieval and rank the useful evidence Learning mechanisms · 13 min
To explore52 Retrieve evidence and condition an answer on it Learning mechanisms · 11 min
To explore53 Keep retrieved evidence current, permitted, and resistant to manipulation Learning mechanisms · 11 min
To explore54 Protect tools and sensitive data around the model Learning mechanisms · 12 min
To explore55 Who is represented by the data? Learning mechanisms · 14 min
To explore56 Decide what success means before training Learning mechanisms · 12 min
To exploreChapter 9 · Lessons 57–63 Working with uncertainty Explore learning to predict; working with uncertainty; checking reliability and behavior; and supporting ideas. 7 lessons · 0 of 7 core ideas demonstrated
57
Look inside the average score Learning mechanisms · 14 min
To explore58 Probability, likelihood, and what is unknown Learning mechanisms · 11 min
To explore59 Update a belief using new evidence Learning mechanisms · 13 min
To explore60 Value a choice and its later consequences Math preparation · 12 min
To explore61 Turn a probability into a justified action Learning mechanisms · 11 min
To explore62 Measure the behavior that the task actually needs Learning mechanisms · 14 min
To explore63 Decide whose problem the system solves and who bears its errors Learning mechanisms · 12 min
To exploreChapter 10 · Lessons 64–71 Building and operating an AI app Explore building and operating an AI app; checking reliability and behavior; putting the pieces together. 8 lessons · 0 of 8 core ideas demonstrated
64
Choose a useful problem before choosing a model Learning mechanisms · 14 min
To explore65 Keep training and serving connected to the same definitions Learning mechanisms · 12 min
To explore66 Release changes with evidence and a recovery path Learning mechanisms · 14 min
To explore67 Notice when the production task changes Learning mechanisms · 14 min
To explore68 Build a test whose score supports the intended claim Learning mechanisms · 12 min
To explore69 Treat evaluators as fallible measurement instruments Learning mechanisms · 17 min
To explore70 Give people useful control over model-assisted work Learning mechanisms · 13 min
To explore71 Project: trace a grounded answer and a controlled tool action Learning mechanisms · 90 min
To exploreOptional extensions and comparisons (14)
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.Misuse in practice: jailbreaks, deepfakes, and provenanceA familiar face or voice is no longer proof of who is speaking. Learn how misuse works and the checks that still hold.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.Coordinate several decision-makers without assuming independent judgmentWhen several agents collaborate, who does what, and how do their mistakes compound?Learn when other decision-makers are learning tooLearning when opponents learn too: self-play, equilibria, and moving targets.Use tools to check work within an explicit stopping policyLet an agent call a calculator or run code, and decide when it should stop.Turn checkable outcomes into a learning signalTrain agents on tasks with checkable answers, like math and code, and watch for reward hacking.Choose whether to score the result, the steps, or bothReward agents for correct results, sound steps, or both, and see how each can be gamed.Distinguish manipulated inputs, training data, and model artifactsSee how attackers target inputs, training data, and downloaded model files, and how agents get exposed.Align measured behavior with intended human constraintsWhat happens when an agent optimizes the wrong target, and how people keep meaningful control.Assess labor, access, resources, and accountability across the lifecycleFollow who gains and who pays when agents take over tasks: jobs, access, energy, and accountability.Discuss broad intelligence and experience without overstating evidenceCan an agent be 'generally intelligent' or conscious? Separate the testable questions from the hype.