Getting Started with RAG
RAG — retrieval-augmented generation — is one of the most practically useful AI patterns I’ve encountered.
The idea is simple: instead of relying on what a language model memorised during training, you retrieve relevant information at query time and feed it into the model’s context. The model then generates a response grounded in that retrieved information.
Why It Matters for Product Teams
The best AI products I’ve seen don’t ask “what can the model do?” They ask “what does the user need, and how do we get the model the information it needs to help?”
RAG is often the answer.
A Simple Example
Imagine a customer support bot for a SaaS product. Without RAG, it hallucinates policy details. With RAG, it retrieves the actual documentation before answering.
The difference isn’t the model. It’s the architecture.
Related Musings
Buttons Were for Humans
A 60-message Slack debate about a pop-up made me wonder — if agents are increasingly the ones navigating the software we build, who are we still designing for?
May 7, 2026 LeadershipOrda Found Its Home
There is a feeling I have never been able to fully describe. You walk into a restaurant you have never been to — maybe you found it on your way somewhere, maybe you just followed your nose — and you notice it. The green interface on the tablet at the counter. The Orda screen.
Mar 31, 2026