Field notes on shipping LLM systems to production: retrieval and ranking, determinism at temperature zero, vLLM serving, and the data jobs nobody puts on call.https://salvadorfcriado.com/blog/enThu, 10 Sep 2026 00:00:00 GMTmail@salvadorfcriado.com (Salvador F. Criado)mail@salvadorfcriado.com (Salvador F. Criado)1440https://salvadorfcriado.com/blog/the-half-nobody-put-on-call/https://salvadorfcriado.com/blog/the-half-nobody-put-on-call/Nobody's RAG system breaks — it quietly stops being right. The jobs nobody wrote down, three mechanisms that make them safe, and what to put on a dashboard.Thu, 10 Sep 2026 00:00:00 GMTLLMOpsData EngineeringRAGmail@salvadorfcriado.com (Salvador F. Criado)https://salvadorfcriado.com/blog/temperature-zero-is-not-deterministic/https://salvadorfcriado.com/blog/temperature-zero-is-not-deterministic/Same prompt, same model, different answer. The mechanism behind non-determinism, the arithmetic that kills agent pilots, and what to do about it.Thu, 03 Sep 2026 00:00:00 GMTLLM ServingEvaluation & MonitoringRegulation & Governancemail@salvadorfcriado.com (Salvador F. Criado)https://salvadorfcriado.com/blog/rag-ranking-not-retrieval/https://salvadorfcriado.com/blog/rag-ranking-not-retrieval/The document was in the index and the answer was still wrong. How to tell a retrieval failure from a ranking failure, what to fix first, and what each costs.Thu, 27 Aug 2026 00:00:00 GMTRAGSearch & RetrievalEvaluation & Monitoringmail@salvadorfcriado.com (Salvador F. Criado)https://salvadorfcriado.com/blog/gates-not-orchestration/https://salvadorfcriado.com/blog/gates-not-orchestration/The orchestration in an AI content pipeline is the boring part. What decides whether text ships is a set of model-free functions with an exit code.Tue, 25 Aug 2026 00:00:00 GMTLLMOpsEvaluation & Monitoringmail@salvadorfcriado.com (Salvador F. Criado)