News for hackers. Stuff that matters.

A comment on Show HN: Safety layer between AI agents and databases. Parent comment

Re:Show HN: Safety layer between AI agents and databases by k-taro56 on Monday May 04, 2026 @10:36AM (#48009331)
Nice concept! I’m concerned about that LLM might discover `faz.yaml` and directly access the databases. Wouldn’t it be more deterministic and safer to wrap the database itself and use a safety-pipeline-enabled DB instead?
[ Parent | on HN ]
Re:Show HN: Safety layer between AI agents and databases by debarshri on Monday May 04, 2026 @10:55AM (#48009518)
It will definitely do that. That we believe you have to make it protocol aware. For eg. if it mysql, it should be proxy that translates as is. then it can't by pass. Also, the proxy should not reveal real credentials.
[ Parent | on HN ]
Re:Show HN: Safety layer between AI agents and databases by k-taro56 on Monday May 04, 2026 @11:06AM (#48009658)
That’s awesome! When the time comes, definitely do a show HN post. I’m looking forward to it!
[ Parent | on HN ]