Prompt optimization¶

Prompt optimization now has its own section:

Topic	Page
Overview and choosing an entry point	Optimization overview
The fit loop step by step	How it works
Metrics, LLM judges, composite objectives, losses	Metrics, judges & loss
Data roles and the anti-overfitting rules	Generalization & overfitting
Dataset format and augmentation	Datasets & augmentation
`compile` / `fit` / `evaluate`, `train_and_report`	Class agents
`PromptFitter` and every option	Low level: PromptFitter
Reading the before/after report	Reports
`agentomatic optimize` and `PromptOptimizer`	CLI & legacy API
Runnable scripts	Examples

Modern Python API: `PromptFitter`¶