[ivanivanka]

Cool experiment. I like that you’re running it live, with real constraints, and you shared a concrete failure mode plus fix instead of hand-wavy “autonomous” claims.

What’s the “trust primitive” you think will make skeptical people comfortable letting agents move money without humans, and how do you package that into a real product beyond the demo?

[pokot0]

Hi! Yes, the premise is exactly to review how 'stable' agents would be if left unsupervised in an end-2-end scenario.

But this is probably unrealistic now, hence the experiment. I think people will be less skeptical the more they interact with these kind of entities and slowly develop trust.

That's why we developed agents with an identity and primarily around email in order to 'plug' them into company processes slowly and naturally. That's the core idea of the main project this experiment spawn off of.