What area would you NEVER trust to Ai, in your inbox?
by•
I mainly follow the principle of "reversibility".
EG. An archived newsletter or a starred investor email can be always reversed.
If ai is right -> makes my life easier
If ai is wrong -> doesn't hurt me
Meanwhile, I would NEVER let ai auto-send things (especially to other humans) for me.
Because no matter how accurate its tonality is to me,
no matter how well it understands my context,
I just don't... Maybe there's some kinda humanity in pressing "send" yourself!?
What about you? Where would you draw the line? Or just raw-dog it and trust the ai?
98 views
Replies
Hello Peter, I like this approach. AI sorting and organizing feels easy to trust, but speaking for you is a completely different level.
@shawn_idrees I agree with the reversibility idea. AI feels much safer when it can help without making permanent decisions on my behalf.
@shawn_idrees I would trust AI with cleaning my inbox, finding old information, and suggesting replies. But sending important messages would still need my approval.
@shawn_idrees Exactly. Let AI sort the inbox, not impersonate my social skills.
The moment it starts saying "hope you’re well" on my behalf, I want a big red human approval button.
Dirac
@shawn_idrees Hey Shawn, completely on-board with this. Would you still be comfortable with sharing your inbox with Ai or not?
The send button still feels like a human responsibility.
Dirac
@alistair_james1 For me as well. Dirac's send button is manually pressed.
@peterz_shu I would rather miss an optimization than send the wrong message.
Dirac
@caleb_jonathan I 100% agree with that.
I draw the line at anything that speaks for me.
Dirac
@ethan_marshall So, anything that other people can see?
Money decisions should never be one click away from AI.
Dirac
@delaney_rose1 EG. investors? Fully understand:)
Anything irreversible deserves a human review.
AI can craft, but I want the final say.
Dirac
@brielle_marie And that's the Dirac morning brief for ya!
I agree on your point but more than that i would'nt even want ai to look at my banking mails.
Dirac
@nischay_kashyap You can manage areas of your inbox and choose what to shut/privatize in Dirac
I like the reversibility principle. I would add one more layer: does the AI action change someone else's reality, or only organize your own view?
For me:
- safe: summarize, classify, draft, highlight risk, suggest a next step
- caution: archive, label, prioritize, change CRM/status fields
- human-only: send, commit money, approve, reject, delete, or make a promise on my behalf
That distinction keeps coming up across products. With ReplyFlow, the safest workflow is test-mode or draft replies before connecting a live customer channel. With PayWise, AI can suggest which payment or debt needs attention, but the user should still make the actual money decision. With RaiseReady, AI can expose missing assumptions in a funding plan, but it should not pretend the business is ready before the owner verifies the numbers.
So yes, reversible actions are a good first filter. External consequences are the second filter.
Dirac
@estreamedia Yeah that is another great point!
You're onto something here...
And this is not just applicable for email alone. But most ai-related apps out there should follow this.
Dirac
Some great comments We Got ------->