aaronon·先月·議論yeah, not really, actually. in my opinion, they may work, but with tradeoffsapi wrappers are safe, but they kill flexibility of AI agent and will have massive maintenance bottleneckdb-level security is a great runtime boundary, but it is completely disconnected from application business logic
aaronon·先月·議論I like that this feels driven by a coherent design philosophy. and the emphasis on AI security is very timely as AI-generated code becomes more common
api wrappers are safe, but they kill flexibility of AI agent and will have massive maintenance bottleneck
db-level security is a great runtime boundary, but it is completely disconnected from application business logic