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.
More from coding & agent
- Dev deletes all ADRs: 49% superseded in days, codebase is now your source of truth — sloppenheimer · 2026-11-20
- Anthropic opens Claude Forward Deployed Engineer learning path, ~9.5 hours self-paced — leslysandra · 2026-11-20
- Google open-sources Sashiko, a Gemini agent that cut Linux post-merge fix rates 35% — rseroter · 2026-11-20
- boxd adds 8 more integrations including Dify, n8n, LangChain, and Neon — JensHonack · 2026-11-20
- OpenAI updates prompting guidance for live-1.1: languages and regional accents — pbbakkum · 2026-11-20
- Rippling AI lets any employee prompt their way to custom business tools — andreisavu · 2026-11-20