Prompt Optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a prompt, when they arrive from the workbench's "Optimize this prompt" menu item, or when they want their bot to answer better. Bootstraps a missing dataset or evaluator first.

langwatch Updated 5k repo stars
LangWatch: Agent Observability & Evals for AI Platform teams

File contents

langwatch/langwatch commit 29de8afd92

Frequently asked questions

npx get-skill add langwatch/prompt-optimization-2