Notes on systems, search, and AI infrastructure.

Hybrid search becomes a systems design problem once score normalization, query routing, and operational tuning enter the picture.

Most RAG stacks move too quickly from prompt to retrieval. A resolver layer improves precision by decomposing intent, extracting entities, and converting ambiguous language into structured search actions.

When the downstream consumer is a retrieval system or model instead of an analyst, pipeline design tolerances shrink. Chunking, metadata quality, schema stability, and data contracts become product-level concerns.