Seat Reservation Required Education Session
Thu • Sep 17 • 1:15pm – 2:00pm ET • Room 205
How to Stop AI Agents from Making Stuff Up
Today's AI models make stuff up far less often than a year ago - and AI agents built on them fail more expensively than ever. No contradiction: the better the model, the more we trust it, the bigger the jobs we hand it, and the subtler the mistakes that slip through. You'll learn to judge any agent by the three questions that decide whether its output can be trusted: What is it allowed to do? What is it allowed to trust? What is it allowed to send? You'll leave with real failure stories, the fixes that caught them, and a checklist to run on your own agents the same afternoon.
Session Speakers:
Nejc (Nates) SkoberneCEO @ Sellestial
Nejc is CEO of Sellestial, the AI-powered data layer for HubSpot, processing millions of CRM records through governed pipelines. He holds a Ph.D. in Computer Science and has built three tech companies at the intersection of AI and B2B operations. He teaches a hands-on AI for RevOps course focused on deploying AI that d…
Related Sessions
Be There at UNBOUND 2026
Boston. September 16–18. Three days designed to help you move beyond outdated playbooks. Break beyond the limits that defined yesterday. Be unstoppable.
