For the last two weeks, I've started a personal 100-day challenge to study and build around what I've been calling a "Company Brain." I'm trying to understand what a company would need beyond search or RAG to actually make better decisions.
Most of what I see today approaches it as search, RAG, memory, or AI agents. I'm not convinced that's the right way to do it
If you've built something, researched it, or have strong opinions, I want to understand your thinking
Interesting to see verification moving into the agent payment layer.
are you seeing more risk from “incorrect execution” vs “unauthorized execution”. Feels like both problems are emerging at the same time as agents start touching money.
The separation between “agent reasoning” and “execution authority” is definitely becoming a real design pattern.
what kinds of actions people are most afraid to let agents execute today. Is it mostly infra mutations, or business-facing actions like refunds/credits too?
For the last two weeks, I've started a personal 100-day challenge to study and build around what I've been calling a "Company Brain." I'm trying to understand what a company would need beyond search or RAG to actually make better decisions.
Most of what I see today approaches it as search, RAG, memory, or AI agents. I'm not convinced that's the right way to do it
If you've built something, researched it, or have strong opinions, I want to understand your thinking