BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Find Local//findlocal.community//EN CALSCALE:GREGORIAN METHOD:PUBLISH BEGIN:VTIMEZONE TZID:America/Detroit BEGIN:DAYLIGHT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:25897556-7bf7-4821-ab02-067aa923e97a@findlocal.community DTSTAMP:20261026T183243Z DTSTART;TZID=America/Detroit:20261026T110000 DTEND;TZID=America/Detroit:20261026T130000 SUMMARY:AI Clinic Lab | Productionizing Agentic Workflows: Supervised AI Agents That Actually Ship (Hybrid) DESCRIPTION:Most agent demos fail in production for the same reason: they ’re given autonomy before they’ve earned trust. This session is a pr actitioner’s look at how a growth agency serving legal\, healthcare an d professional-services firms runs AI agents in daily operations\, and w hy “draft and propose\, humans approve†beats “fully autonomous.†We’ll walk through the real stack: Hermes-based agents with local and cloud models\; a shared company “brain†that gives every agent the sa me curated context and keeps live systems authoritative\; and a coordina tion board where agents hand off bounded tasks and flag decisions that b elong to a person. You’ll see the guardrails that make it safe: approv al gates on anything client-facing\, per-agent credentials scoped to a h uman owner\, and reviewed pull requests for every change to shared knowl edge. Attendees leave with a practical blueprint for deciding what to au tomate\, what to gate\, and how to expand agent scope without losing con trol.\n\nMore info: https://events.umich.edu/event/153807\n\nhttps://fin dlocal.community/event/25897556-7bf7-4821-ab02-067aa923e97a LOCATION:The University of Michigan\, Ann Arbor\, MI URL:https://findlocal.community/event/25897556-7bf7-4821-ab02-067aa923e97 a STATUS:CONFIRMED SEQUENCE:0 END:VEVENT END:VCALENDAR