#langsmith

Zero-cost architectural decisions — a prompt registry, per-block model config, and three BigQuery columns — that cost nothing to add now and unlock DSPy optimisation, LangSmith experiments, and behavioural flywheels later.

Your retrieval pipeline returns results. But does it return the right results? How New Computer used LangSmith's experiment framework to achieve 50% higher recall and 40% higher precision in agentic memory retrieval — and what you can steal from their approach.