DSPy, from Stanford NLP: define task signatures and let optimizers tune prompts

stanfordnlp · x · 2026-09-26

DSPy, the framework that started at Stanford NLP, pushes a "program, don't prompt" workflow:

Rather than iteratively tweaking prompt text, developers describe tasks like ordinary programs and let DSPy handle prompt engineering.

Original post →

More from coding & agent

coding & agent channel →