One thing I’ve been bitten by with desktop agents is execution-time safety:
the plan is correct, but a single malformed path or OS call causes real damage.
Do you enforce any guardrails at the tool boundary
(e.g. path sandboxing, network allowlists, dry-run / replay)?
One thing I’ve been bitten by with desktop agents is execution-time safety: the plan is correct, but a single malformed path or OS call causes real damage.
Do you enforce any guardrails at the tool boundary (e.g. path sandboxing, network allowlists, dry-run / replay)?
Curious how you’re thinking about this.