Lessons from securing AI systems at runtime (agents, MCPs, LLMs)1 points·by joyjeetdan·5 maanden geleden·3 comments
joyjeetdan·5 maanden geleden·discussOne thing that surprised us: gateways and logs were useful, but insufficient. The real gaps appeared when execution spanned multiple agents, tools, and identities over time. Would love to hear how others are handling this today.