AI Engineering Notes
Production-minded writing on AI, RAG, and software architecture
A bilingual archive of practical notes on RAG, agentic workflows, microservices, and full-stack engineering.
Subscribe via RSS
Get new posts in your reader when they go live — no email required.
Graph RAGvector databaseshybrid search
May 21, 2026·5 min
Graph RAG vs Vector RAG: When to Use Each
An architecture-focused comparison of Graph RAG and vector RAG: chunking, storage, retrieval behavior, trade-offs, and hybrid search patterns.
RAG pipelineretrieval-augmented generationLLM
May 20, 2026·6 min
Building Production RAG Pipelines: Practical Lessons
Practical lessons for AI engineers on designing a production-ready RAG pipeline with reliability, latency, evaluation, and operations in mind.
LLMContext EngineeringPrompt Engineering
May 20, 2026·4 min
Context Engineering: Building More Reliable LLM Systems in Production
Context engineering is the practice of supplying the right information, in the right form, at the right time. This draft covers practical production lessons for LLM applications.