GEPA: turn failures into useful feedback
Use reflective prompt optimization after the baseline, with a real budget and an untouched final test set.
DSPy
Metrics before optimizers
Define success, measure a baseline, and reserve unseen examples before asking DSPy to improve a program.
Start here: learn DSPy by improving one small program
A practical path from signatures to evaluation, prompt optimization, and a saved program you can compare honestly.