4 min
When your n8n automation needs a brain
n8n is excellent at deterministic workflows and quietly terrible at ambiguity. Here's where the ceiling is, and when an AI agent loop actually earns its place.
n8n · automation · agents
04 — Transmissions
Field notes from the practice.
What we learn engineering agents, retrieval, and orchestration — written down plainly, for people building the same things.
5 min
Production RAG that doesn't hallucinate
Most RAG failures are retrieval failures wearing a generation costume. Chunking, hybrid retrieval, grounding, and the evals that catch problems before users do.
rag · retrieval · llm
4 min
Why prompt refinement should run on your device
RefineIQ rewrites rough AI prompts into clear ones with a language model that runs entirely in your browser. The architecture, the trade-offs, and why zero backend is the feature.
refineiq · on-device ai · privacy
4 min
Planner, critic, verifier: orchestration patterns that survive production
Multi-agent systems fail in predictable ways. The patterns that keep them deterministic where it counts — role separation, verification gates, and budgets on everything.
agents · orchestration · llm