David Alimi — AI engineer writing about what I actually build.
Building in public. Documenting what I learn as an AI Engineer.
Currently building
Torah Study AI
Production RAG pipeline on 3.5M sacred texts. Hybrid search, Cohere reranking, strict anti-hallucination guardrails. Built with FastAPI, Weaviate, and Gemini.
Knowledge base
AI Engineering, one notion at a time
38 notions across 13 domains - LLMs, RAG, agents, MCP, prompt caching, evaluations, and more. Each page: TL;DR, problem, how it works, 2026 relevance.
Recent writing
2026
5 techniques to make your RAG system actually work
A vanilla RAG retrieves documents and hopes for the best. Here are 5 techniques that production RAG systems use to go from 'it works sometimes' to 'it works reliably'.
2026
How a RAG Server Works, Step by Step
A RAG server has two phases: prepare the knowledge base once, then answer questions forever. Here is what happens at each step.
2026
Why strict RAG matters on sensitive data
When your LLM can fall back to general knowledge, it will. On religious texts, legal docs, or medical data, that is not acceptable. Here is why.
2026
How to handle bad RAG results gracefully
Your RAG system found nothing relevant. Now what? The industry patterns for fallback strategies, relevance thresholds, and honest abstention.
Newsletter
A short dispatch when I ship something or break it. No hype. Unsubscribe anytime.