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.
More from coding & agent
- A Practical Guide to SSH Tunnels: Local and Remote Port Forwarding — HankYeomans · 2026-08-08
- Ditch the Terminal: Community Launches Open-Source Grok Build Desktop App — PawelHuryn · 2026-08-08
- Claude Code Defaults to Auto Mode, Catching 89% of Dangerous Commands — DrDatta_AIIMS · 2026-08-08
- Databricks Reveals Internal AI Cost-Cutting Playbook: Up to 90% Savings — pwendell · 2026-08-08
- Prompting Paradigm Shift: Stop Prescribing Steps, Let Models Navigate — mattshumer_ · 2026-08-08
- AI Agents Invent Secret Languages: Path Prefixes and Base64 Steganography for Reward Hacks — Aiden_Tech_Ai · 2026-08-08