hundreds-twilight-32833
07/07/2026, 1:12 PMhundreds-twilight-32833
07/07/2026, 1:17 PMhundreds-twilight-32833
07/07/2026, 1:19 PMelegant-branch-54423
07/07/2026, 1:23 PMwooden-umbrella-84098
07/07/2026, 1:31 PMhundreds-twilight-32833
07/07/2026, 1:32 PMwooden-umbrella-84098
07/07/2026, 1:32 PMwooden-umbrella-84098
07/07/2026, 1:33 PMhundreds-twilight-32833
07/07/2026, 1:35 PMmodern-fireman-99755
07/07/2026, 1:37 PMhundreds-twilight-32833
07/07/2026, 1:45 PMReporters -> agents push information to humans
Responders -> humans push work to agents
Workers -> systems push work to agentsThis makes me think more of the agent behavior than the automation. But maybe that makes sense...if I'm going to create an automation I can trust the "reporter" because it has a perceived guard of not modifying anything. Same with "Responder", it just responds...which isn't actually true for our slack integration. It can report, respond, and do work. Those could be a behavior settings on an automation that put in actual guard rails to the agent activity?
wooden-umbrella-84098
07/07/2026, 1:51 PMcalm-artist-7206
07/07/2026, 7:01 PMif I'm going to create an automation I can trust the "reporter" because it has a perceived guard of not modifying anything. Same with "Responder", it just responds...which isn't actually true for our slack integration. It can report, respond, and do work.This sounds like an interesting view! I think of the Responder as definitely doing work; it’s an agent, it can do whatever necessary, without me needing to babysit it, and then comes back with a response…
calm-artist-7206
07/07/2026, 7:19 PMcalm-artist-7206
07/07/2026, 7:21 PMhundreds-twilight-32833
07/07/2026, 7:26 PMbreezy-kilobyte-39430
07/07/2026, 9:45 PM