> ## Documentation Index
> Fetch the complete documentation index at: https://docs.withwhile.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Install with `pip install whileai`; import as `import whileai as wai`.
> Run the offline path first (`simulator=False`, `wai.seeded_agent`, a callable judge); no key is needed for it.
> Report every pass rate with its interval and n, as `scored.pass_at` prints it.

# Learn post-training from zero

> Seven short lessons for an engineer who has never trained a model. Each one runs offline, with no key, in under a minute.

You can read Python and run a script. You have never trained a model, and
the words in the quickstart (rollout, reward, held-out, pass\@1) are a
jump. These seven lessons close that jump one word at a time.

Each lesson says the idea in plain words first, then names the term the
field uses for it, then runs it. Every snippet runs on a laptop with no
key and no network, and the output shown is what it printed. At the end
you will be able to read the [quickstart](/get-started/quickstart) and
know what every line is for.

<Steps>
  <Step title="A model learns from examples, not from instructions">
    What training changes that a prompt cannot. Pretraining, post-training,
    SFT and RL, in one page. [Read it](/learn/what-training-does).
  </Step>

  <Step title="One saved conversation is a rollout">
    The row: the ask, the tool calls, the reply. Where rows come from when
    you have no traffic. [Read it](/learn/what-a-rollout-is).
  </Step>

  <Step title="A reward is a score you can defend">
    A program that checks the answer, or a model that reads it. How to
    check the checker. [Read it](/learn/what-a-reward-is).
  </Step>

  <Step title="A pass rate without an interval is a guess">
    pass\@1, the interval, and how many tasks a real result needs.
    [Read it](/learn/why-one-number-is-not-a-result).
  </Step>

  <Step title="The test the model never sees is the only score that counts">
    The held-out set, and the check that no training row is a copy of a
    test row. [Read it](/learn/the-held-out-set).
  </Step>

  <Step title="Train on what the model gets right sometimes">
    Which rows to keep for SFT, which for RL, and why a task the model
    always passes teaches nothing. [Read it](/learn/which-rows-to-train-on).
  </Step>

  <Step title="Training is done when the held-out score moved">
    Export, train on your own compute, and prove the change with a paired
    before and after. [Read it](/learn/train-and-prove).
  </Step>
</Steps>

## What you need

```bash theme={"theme":"vitesse-dark"}
pip install whileai
```

Python 3.10 to 3.13. No account, no key. The lessons use a stand-in agent
that makes mistakes on purpose and records them, so there is always an
answer key to check against.

## The whole course in one paragraph

A language model has read the internet and never worked at your company.
A prompt is a note on its monitor. Training changes what it knows how to
do. To train it you need rows (one saved conversation each), a score per
row (a program if one can check, a model if not, and you check the
model), and a test set the model never sees. You keep the rows that
teach something, train on your own compute, and the result counts only
when the score on the test set moves by more than the noise. Then the
next day's traffic is the next training set.