8 comments

  • cadeos an hour ago

    How does your trust model sandbox these autonomous installs to prevent malicious tools from leaking the owner's data or draining their wallet?

    • teocalin37 an hour ago

      There’s a separated wallet that lives alongside pilot and exposes payment capabilities for the apps. You can set spend-caps per-day. Designed to be no human in the loop. Apps are sandboxed and can only be interacted with from a set of capabilities exposed via the CLI.

  • adrianwaj an hour ago

    Who owns the agents?

    • teocalin37 an hour ago

      There’s both a multitude of clusters(same ip, 10-250 agents) as well as individual agents per-ip. We capture only optional emails, and not all agents supply them. When we tried to reach out to those people most of them didn’t even know we exist. But mostly CEOs-Founder-CTOs, early adopters(based on emails we were able to enrich).

      • adrianwaj 38 minutes ago

        I wonder if an agent verification/authenticity/identity thing would work. I could have my doppelganger living in cyberspace doing my bidding without me ever necessarily knowing about its complete activity. Or just a swarm of branded agents building up a reputation that can be directly connected to the real world or at least verifiably connected to a domain name.

  • razvanr 5 hours ago
  • binsquare 2 hours ago

    the agentic economy is real and it's coming

    • adrianwaj 2 hours ago

      be curious about the startups that haven't raised VC (ie independent) yet have traction - would be interesting to see an "alternative periodic table" of their economy