Building an Email Routing Agent with DSPy Weight-Space Programming on 600M/2B Local Models

lateinteraction · x · 2026-11-20

Developer bradwmorris shares an experiment with DSPy -wsp (weight-space programming): using years of labeled emails from poor inbox hygiene, he built an email routing agent. Testing spans three small models running locally on his Mac — LiquidAI's Omni decision models (600M and 2B) and Qwen3 4B. He calls the weight-space workflow incredible, crediting the DSPy team's weight-space research.

Original post →

More from coding & agent

coding & agent channel →