[raxxorraxor]

I currently don't allow agents to write arbitrary queries. But if I wanted to, I would probably just use the security model of the DB and give the AI a user that is restricted to data it can access.

AI is fairly apt at writing efficient queries for that matter and I use it a lot for this purpose.

[Hoshang07]

that's a good baseline..db rbac locks scope, but i guess not behavior. inside that schema the agent can still fire off wide scans, weird joins, or grab way more rows than needed.. Ai can write apt queries for sure but there's always a dependancy on the kinda prompt it gets. you may also lose semantic clarity and telemetry .. no way to know if it actually pulled the right data. how would you enforce “only these lookups” or “only these joins” with just db perms? is there a way?