Real Python Podcast: Programmatically Developing LLM Prompts With DSPy

lateinteraction · x · 2026-08-08

The Real Python podcast featured Brett Kennedy discussing how to programmatically develop and optimize LLM prompts using the DSPy framework.

As LLMs become embedded in production software, manually written prompts grow brittle and hard to maintain. The episode introduces how DSPy uses declarative signatures for inputs/outputs and allows developers to compile and tune prompts. The discussion also covers DSPy's application in RAG and business tools, moving towards a new level of abstraction in prompting.

Original post →

More from coding & agent

coding & agent channel →