# How-to guides

**Task-shaped: you already know what you want, and this tells you how.** If you are still working
out what you want, read an explanation page instead; if you know the name of the setting and want
its default, that is [reference](../reference/).

Begin with the [quickstart](../tutorial/README.md) for a running stack. Individual guides
record their own examples and validation; a documentation refresh does not represent
a new live-provider run.

- [Configure Pointsman](configure-pointsman.md) - environment, YAML and runtime records; worked examples, activation, verification and rollback.
- [Prepare a deployment](deploy.md) - network boundaries, persistence, resource sizing and rollout validation.
- [Add a provider and a model](add-a-provider-and-a-model.md) - any OpenAI-compatible vendor as
  a database row: create disabled, probe, enable, prove a request landed there.
- [Add a second key to a provider, and rotate one](add-a-second-provider-key.md) - a sibling
  credential, the ledger proof of which key paid, a rotation with a stream in flight, a per-key
  ceiling, and every refusal the door makes.
- [Build a team hierarchy](build-a-team-hierarchy.md) - an authored team scope, a correctly
  caged team admin, a key homed at the team, and a budget whose binding the server names.
- [Issue a key and give it a budget](issue-keys-and-set-budgets.md) - the admin login dance, an
  organisation, a monthly cap, and a key that draws on it.
- [Send some of your traffic to a different model](split-traffic-between-models.md) - canary
  deploys, A/B tests and gradual migrations, which are the same mechanism with different numbers.
- [Turn on outcome learning](turn-on-outcome-learning.md) - the bandit strategy: decision ids,
  reporting how answers turned out, and reading the belief surface while it learns.
- [Route by task with an external classifier](jev-routing.md) - the opt-in Jev strategy:
  what it exports and to whom, the operator-paid bounds, the ranking it applies inside the
  shortlist, the fallback on every abstention, and the offline evaluation to run before
  trusting it.
- [Route only to models with quality evidence](quality-guarded-routing.md) - the experimental
  quality-guarded strategy: register validators, freeze an evaluation, adjudicate one sealed batch,
  preview and promote a policy, read what served each request, roll back without reviving expired
  evidence.
- [Write and enforce a guardrail](write-and-enforce-a-guardrail.md) - dry-run against sample
  text, watch in monitor mode, then enforce; including the misconfigurations made writing it.
- [Tune the semantic cache](tune-the-semantic-cache.md) - the similarity threshold, the evidence
  to tune it from, and what the cache refuses to do.
- [Work out what happened to a request](diagnose-a-request.md) - from a request id, or from the
  queryable record when you do not have one.