Building Without Foundations Means Reinventing RAG, Badly
- Source
- x.com
- Date
Another year of rapid AI advances has created more opportunities than ever for anyone — including those just entering the field — to build software. In fact, many companies just can’t find enough skilled AI talent. Every winter holiday, I spend some time learning and building, and I hope you will too. This helps me sharpen old skills and learn new ones, and it can help you grow your career in tech. To be skilled at building AI systems, I recommend that you: - Take AI courses - Practice building AI systems - (Optionally) read research papers Let me share why each of these is important. I’ve heard some developers advise others to just plunge into building things without worrying about learning. This is bad advice! Unless you’re already surrounded by a community of experienced AI developers, plunging into building without understanding the foundations of AI means you’ll risk reinventing the wheel or — more likely — reinventing the wheel badly! For example, during interviews with job candidates, I have spoken with developers who reinvented standard RAG document chunking strategies, duplicated existing evaluation techniques for Agentic AI, or ended up with messy LLM context…
Context
Building projects and studying established methods solve different learning problems. In Ng's learning advice, Andrew Ng describes interviewing job candidates who had reinvented standard document- strategies for retrieval or duplicated existing techniques, apparently without knowing those building blocks already existed.
Ng's recommendation is to pair structured learning with hands-on work. Courses can reveal methods worth reusing, and practice teaches lessons that courses alone do not, as flying teaches what aviation theory cannot. Ng places reading research papers below those two priorities, while valuing it for knowledge not yet translated into accessible formats. The argument rests on Ng's experience, not a controlled comparison of education methods.
- chunking — Splitting documents into passages small enough to embed and retrieve individually — the step that quietly determines whether retrieval works at all.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
- RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Checking sign-in…
Loading comments…