If Dspy is so great, why isn't anyone using it?
For a framework that promises to solve the biggest challenges in AI engineering, this gap is suspicious. Still, companies using Dspy consistently report the same benefits.
JetBlue · Databricks · Zoro UK · VMware · Sephora · Replit
DSPy’s problem isn’t that it’s wrong. It’s that it’s hard. The abstractions are unfamiliar and force you to think a litle bit differently. And what you want right now is not to think differently; you just want the pain to go away.
But I keep watching the same thing happen: people end up implementing a worse version of Dspy. I like to jokingly say there’s a Khattab’s Law now (based off of Greenspun’s Law about Common Lisp):
Any sufficiently complicated AI system contains an ad hoc, informally-specified, bug-ridden implementation of half of DSPy.
You’re going to build these patterns anyway. You’ll just do it worse, after a lot of time, and through a lot of pain.