Re:Launch HN: April (YC S25) – Voice AI to manage your email...
by danenania on Monday August 25, 2025 @09:00PM
(#45021061)
I think you could probably solve it for this use case by just including a confirmation step for potentially destructive actions which is isolated from other context.
[1]: https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-... (currently on the front page)