> ## 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.

# FAQ

> What people ask before they start.

**Who is it for?** Heads of AI, ML and data science, their teams, and the
data teams that own the training data. You do not need a research team to
run a training loop.

**Mid-training or post-training?** Both, though `wai.train` runs the
post-training methods. Mid-training continues training on your domain data
so the model knows your world. Post-training with SFT, DPO or GRPO teaches
it how to behave. Most teams start with post-training.

**Do I have to change my agent?** No. The SDK reads what the agent does,
from its traces or from its tools and policy. The agent keeps running
where it runs today. See [connect your agent](/get-started/connect-your-agent).

**What if my agent is not in production yet?** Describe the behavior you
want in a sentence. That sentence is the policy. The SDK drafts the tools
such an agent would have and runs the conversations against them, so there
is training data before there is traffic.

**Do I need a key?** Not to start. `simulator=False` writes situations
from templates, `seeded_agent` stands in for an agent, and a lambda can
be the judge, all offline. A key adds the hosted situation writer, the
hosted judge, dataset storage, training and serving. See
[install](/get-started/install).

**How do I know it got better?** Every run ends with pass\@1 per task
category, before and after, on a held-out set with a 95% confidence
interval. If the interval includes zero, nothing ships.

**Which models can it train?** Open models you own at the end. Training
runs SFT, DPO, GRPO or a reward model on hosted GPUs. Serving is narrower
than training: an adapter reaches an endpoint only on a served base, today
`Qwen/Qwen3-4B` and `microsoft/phi-4`, and `train` warns when a run will
not. See [the platform reference](/reference/platform).

**Where do the rollouts come from?** From your agent's own tools and
policy. A separate model plays the customer, a mock world answers the tool
calls, and every conversation is scored against a written rubric before it
is kept. See [how it works](/concepts/how-it-works).

**Is the judge another LLM?** Yes, when you do not pass a program. So it
is measured against gold labels, probed with known hacks, versioned by
rubric hash, and drawn from a different model family than the policy. See
[the engine](/concepts/engine).

**What happened to zeroproof?** Same package, renamed in 0.51.
`pip install zeroproof` and `import zeroproof.simulations` still work and
give you `whileai`.