Auto Prompt Creator

What it does

A prompt optimization system that makes Haiku produce outputs indistinguishable from Opus on a defined task. Takes a baseline prompt, scores it against expert ground truth, and mutates it through a phased anneal loop — bootstrap, generalize, polish — with mutation diversity constraints that prevent overfitting. Graduates to a portable library entry when it clears 92% on held-out validation data.

How it works

Features

• ✓Phased mutation loop (bootstrap, generalize, polish) prevents example memorization
• ✓Weighted rubric scoring against train/val/holdout splits
• ✓Auto halt on threshold, plateau, overfitting, or token budget
• ✓Subtractive check at iteration 8 proves generalization, not lookup
• ✓Graduated prompts land in `library/` with full accuracy metadata

Who it's for

• Porting an Opus prompt down to Haiku for a 10x cost cut
• Tuning classification, extraction, or enrichment prompts for production pipelines
• Building a reusable prompt library with measured accuracy per task