The AI Engineering Vocabulary: Evals, Guardrails, RAG and the Words That Actually Matter
Every field has a vocabulary you have to own before anything else makes sense…
Tag
#rag
11 posts
Building Voicebots — Telephonic & Browser, the Real Engineering
Voicebots have quietly become good enough to be genuinely useful — a citizen can…
Knowledge: RAG vs Without RAG
A voicebot that can only chat is a toy; a useful one knows things — your schemes…
Latency: TTFT, TPOT and Prefix Caching
A product team reduced their chatbot’s total response time by 40% and users…
Advanced: Vector Databases
Keyword search matches strings: a search for “car” misses a document that only…
LLM Engineering in Production
Most LLM tutorials stop at “call the API and print the result.” Production doesn…
Real Project — Build a RAG Knowledge Bot
This is the capstone project. Everything you’ve learned across the previous…
Chunking Strategies — What Nobody Tells You
You built a RAG pipeline. You embedded your documents, stored them in a vector…
Building a RAG Pipeline from Scratch
RAG is the most important pattern in production AI. Not because it is clever…
RAG — Give Your AI a Knowledge Base
LLMs know a lot, but they don’t know your data. They can’t read your company…
AI for Developers — Build with LLMs, RAG & Agents
You don’t need a PhD in machine learning to build with AI. You need to know how…