The hardest part of shipping a retrieval-augmented generation system is not getting the first version live. It is knowing when the next change quietly made it worse.
When people talk about prompt caching, they usually frame it as infrastructure optimization. Lower costs. Lower latency. Fewer repeated tokens. All true.
Search is not disappearing. It is being translated.
If you are building serious AI products, the answer is almost never “use the biggest model for everything.”
RAG became the default answer to a lot of AI product questions because it solves a real problem: models do not know your data by default.
Synthetic data is one of the most useful accelerants in AI engineering, and one of the easiest ways to fool yourself.
I think AI browsers are more important than they look at first glance.