sameergh

Joined 7 months ago

Karma

Submissions

Member since

Mar 13

Founder at Sentinely runtime security for AI agents. Building the security layer that stops prompt injection, memory poisoning, and agent drift in production. sentinely.ai

View on Hacker News

Recent submissions

Comment · 7 months ago

Hey there, It's a very good idea to be honest I would like to connect with you :)

Comment · 7 months ago

If this is accurate the US is making itself look unreliable for major energy investment

Comment · 7 months ago

Yes a bit, The hard part now is not coding, it is deciding what is actually worth building

Comment · 7 months ago

Interesting approach to slimming down the framework layer. One thing I've been thinking about as agents get lighter and faster the attack surface for prompt injection and behavioral drift grows. Are you thinking about any security primitives at this layer?