HackerTrans
TopNewTrendsCommentsPastAskShowJobs

joyjeetdan

no profile record

Submissions

Lessons from securing AI systems at runtime (agents, MCPs, LLMs)

1 points·by joyjeetdan·5 miesięcy temu·3 comments

comments

joyjeetdan
·5 miesięcy temu·discuss
One 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.