Blog
Not AI news. One question per post: does this change how you build?
Prompt engineering was a phase. What actually determines whether your agent works in production is what you put in the window, in what order, and what you leave out.
Every time a model ships a bigger window, someone declares retrieval obsolete. The economics and the recall curves both say otherwise — but the architecture is genuinely changing.
Teams spend weeks choosing between LangGraph and CrewAI and zero days deciding how they'll know if it works. The framework question is downstream of a measurement question nobody asked.