The Applied Layer / Pillars
Architecture & Retrieval
The patterns that distinguish production AI from demos.
Pillar 2 of 5 · 2 pieces filed
The patterns that distinguish production AI from demos.
Key findings
- Hybrid retrieval (lexical plus dense plus reranker) consistently outperforms pure-vector retrieval on enterprise corpora.
- Most production failures are retrieval failures, not generation failures. Naive embed-and-retrieve pipelines hover near 60 percent retrieval accuracy at scale.
- Chunking strategy and query rewriting move the needle far more often than the embedding model. The embedding model is rarely the bottleneck once a sensible default is selected.
- Agentic patterns sit on a five-tier maturity ladder. Tiers 1 and 2 (deterministic-with-LLM-glue, tool-using single agents) are broadly production-ready. Tiers 3 to 5 are workload-specific and frequently over-claimed.
- The choice between architectural patterns can be made deterministically given a workload’s corpus characteristics, query complexity, latency budget, error tolerance, and verifiability surface.
From the anchor research
Filed under Architecture & Retrieval
2 pieces filed under this pillar. Members read the body.
Architecture and Retrieval
Title only. Become a Member to read.