Automatic Prompt Optimization
Replace manual prompt tweaking with a metric-driven search that an optimizer runs over the prompt space.
Description
Stop hand-tuning the prompt. Define the task as inputs, outputs, and a metric, then let an optimizer search the prompt space for you. The optimizer proposes prompt variants, scores them on your metric, and keeps the winners. It pays off once you have a clear metric and a labelled example set, and it scales past what a human can tune by hand.
When to apply
Use this when you have a measurable metric, a labelled example set of a few dozen cases or more, and a task stable enough to be worth optimising. It earns its keep on prompts in pipelines and on tasks too fiddly to tune by hand. Don't apply it when you have no metric, since the optimizer has nothing to climb.
What it involves
- Express the task as a program
- Assemble a labelled example set
- Pick a metric
- Choose and run an optimizer
- Lock the winner and re-check
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.