> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/12.-support/best-practices.md).

# Best practices

Stratix best practices — quick reference for new users.

## Evaluations

* Pick 3-5 benchmarks that match your task; resist "more"
* Re-evaluate quarterly as the model frontier moves
* Use spaces for stable configs; one-offs for exploration

## Judges

* GEPA-optimize against ≥30 labels
* Hold out a validation set
* Watch for over-fit (validation agreement << training)

## Continuous evaluation

* Sample production traffic; full corpus is rarely worth it
* Anchor with deterministic rules; reserve judges for residual subjective bar

## Govern

* Wire CI gates after you've trusted the eval interactively
* Per-feature tolerances — not every feature has the same bar

## See also

* [Workflow](/1.-introduction/the-stratix-workflow.md)
* [Concepts](/13.3-concepts-library-+-architecture/concepts-library.md)