--- title: "Node & Neural (@nodeneuralai) | Hashnode" description: "Enterprise AI architecture, explained with working code. Read the latest articles by Node & Neural on Hashnode." url: "https://hashnode.com/@nodeneuralai" --- @nodeneuralai # Node & Neural @nodeneuralai · Joined November 2026 Enterprise AI architecture, explained with working code. ### [Your RAG Agent Is Quoting Deleted Documents (Postgres + pgvector Fix)](https://nodeneuralai.hashnode.dev/your-rag-agent-is-quoting-deleted-documents-postgres-pgvector-fix?utm_source=hashnode&utm_medium=feed) Your RAG agent quoted a deleted contract because its embedding lived in a separate vector database. Keep embeddings in Postgres with pgvector. 6 min read · [nodeneuralai.hashnode.dev](https://nodeneuralai.hashnode.dev/your-rag-agent-is-quoting-deleted-documents-postgres-pgvector-fix?utm_source=hashnode&utm_medium=feed) [4h ago](https://hashnode.com/posts/your-rag-agent-is-quoting-deleted-documents-postgres-pgvector-fix/6af87c4d73981077371cce5c) ### [Never Call an LLM From Your ERP: AI Middleware Architecture](https://nodeneuralai.hashnode.dev/never-call-an-llm-from-your-erp-ai-middleware-architecture?utm_source=hashnode&utm_medium=feed) Your ERP just called an LLM synchronously. The model took 31 seconds. The ERP gave up at 30. Now 1,200 orders are stuck between "paid" and "shipped", and nobody knows which ones the AI already process 4 min read · [nodeneuralai.hashnode.dev](https://nodeneuralai.hashnode.dev/never-call-an-llm-from-your-erp-ai-middleware-architecture?utm_source=hashnode&utm_medium=feed) [Nov 4](https://hashnode.com/posts/never-call-an-llm-from-your-erp-ai-middleware-architecture/6aeb7f002ce1d41176784ef8) ### [LLM Routing: Stop Paying Premium Prices for Simple Prompts](https://nodeneuralai.hashnode.dev/llm-routing-stop-paying-premium-prices-for-simple-prompts?utm_source=hashnode&utm_medium=feed) Route each LLM request to the cheapest model that can handle it, by task and risk instead of prompt length, and validate every answer it returns. 6 min read · [nodeneuralai.hashnode.dev](https://nodeneuralai.hashnode.dev/llm-routing-stop-paying-premium-prices-for-simple-prompts?utm_source=hashnode&utm_medium=feed) [Nov 3](https://hashnode.com/posts/llm-routing-stop-paying-premium-prices-for-simple-prompts/6aea74d1f28f97790e0c9015)